Prepare for and practice interview questions from Joby Aviation.

Joby Aviation Interview Questions

Joby Aviation Interview Guides

Machine Learning

Encoding Categorical Features

Bank Fraud Model

Type-ahead Search

Food Prep Features

How to model merchant acquisition in a new market?

Merchant Acquisition

Data Structures & Algorithms

Given a list of integers, and an integer N, write a function to find all combinations that sum to the value N.

Sum to N

Write code to generate a sample from a multinomial distribution with keys 

Drawing Balls From Bin

Weighted Keys

Simulate rolling a dice from a continuous uniform distribution

Dice Rolls From Continuous Uniform

Justify an array of words given an arbitrary line width.

Max Width

Write a query to select the top 3 departments with at least ten employees and rank them according to the percentage of their employees making over 100K in salary.

Employee Salaries

User Experience Percentage

Distance Traveled

Download Facts

Select a (weight) random driver from the database.

Random Weighted Driver

Statistics

P-value to a Layman

What are the assumptions of linear regression?

Assumptions of Linear Regression

A new airline came out as the fastest average boarding times compared to other airlines.  What factors could have biased this result and what would you look into?

Boarding Times Bias

MLE vs MAP

Describe linear regression to various audiences with different levels of knowledge.

Explaining Linear Regression to Different Audiences

Business Case

Instant Eat Reintroduction

Delivery Fees

Apartment Pricing

How to boost presence in high-demand city areas

Incentive Scheme

How would you create a policy for refunds with regards to balancing customer sentiment and goodwill versus revenue tradeoffs?

Food Delivery Refund Policy

When an interviewer asks a question along the lines of:

<ul>
<li>What would your current manager say about you? What constructive criticisms might he give?</li>
<li>What are your three biggest strengths and weaknesses you have identified in yourself?</li>
</ul>

How would you respond?

When asked about your strengths in an interview, what is an effective way to respond?

When asked about your strengths in an interview, what is an effective way to respond?

Your Strengths and Weaknesses I

Which of the following is an acceptable strategy when discussing weaknesses in an interview?

Which of the following is an acceptable strategy when discussing weaknesses in an interview?

Your Strengths and Weaknesses II

What do you tell an interviewer when they ask you what your strengths and weaknesses are?

Your Strengths and Weaknesses

Brainteasers

How would you explain what a p-value is to someone who is not technical?

What does a p-value in a statistical test represent?

What does a p-value in a statistical test represent?

P-value to a Layman I

In a statistical test, how does a low p-value (less than 0.05) influence our decision about the null hypothesis?

In a statistical test, how does a low p-value (less than 0.05) influence our decision about the null hypothesis?

P-value to a Layman II

What are the assumptions of linear regression?

Which assumption of the residuals of the standard linear regression model can not be overcome by increasing the sample size?

Regression assumptions

How would you handle the data preparation for building a machine learning model using imbalanced data?

Addressing imbalanced data in machine learning through carefully prepared techniques.

Data Preparation for Imbalanced Data

Talk about a time when you had trouble communicating with stakeholders. How were you able to overcome it?

Strategically resolving misaligned expectations with stakeholders for a successful project outcome

Stakeholder Communication

Analytics

Explain the difference between the XGBoost and random forest algorithms and give an example where you would use one over the other.

Why might a data scientist choose to use XGBoost instead of Random Forest for a particular machine learning task?

Why might a data scientist choose to use XGBoost instead of Random Forest for a particular machine learning task?

XGBoost vs Random Forest: Choice

Xgboost vs Random Forest

How does random forest generate the forest? Additionally, why would we use it over other algorithms such as logistic regression?

What happens when you average the output on multiple decision trees?

What happens when you average the output on multiple decision trees?

Average Trees

Random Forest Explanation

Let’s say that you work at a B2B SAAS company that’s interested in testing the pricing of different levels of subscriptions.

Your project manager comes to you and asks you to run a two-week-long A/B test to test an increase in pricing.

How would you approach designing this test? How would you determine whether the increase in pricing is a good business decision?

Testing Price Increase

A/B Testing

Let’s say that your company is running a standard control and variant AB test on a feature to increase conversion rates on the landing page. The PM checks the results and finds a .04 p-value.

How would you assess the validity of the result?

Experiment Validity

Let’s say that you work at a bank that wants to build a model to detect fraud on the platform.

The bank wants to implement a text messaging service in addition that will text customers when the model detects a fraudulent transaction in order for the customer to approve or deny the transaction with a text response.

How would we build this model?

Let’s say that you work at a bank that wants to build a model to detect fraud on the platform.

The bank wants to implement a text messaging service that will text customers when the model detects a fraudulent transaction in order for the customer to approve or deny the transaction with a text response.

Which statement is true?

Let's say that you work at a bank that wants to build a model to detect fraud on the platform.

The bank wants to implement a text messaging service that will text customers when the model detects a fraudulent transaction in order for the customer to approve or deny the transaction with a text response.

Which statement is true?

What’s the relationship between PCA and K-means clustering?

What does the variable “k” in k-means clustering refer to?

What does the variable "k" in k-means clustering refer to?

Input of K-means

PCA and K-Means

In the context of hypothesis testing, what are type I errors (type one errors) and type II errors (type two errors)? What is the difference between the two?

Bonus: Describe the probability of making each type of error mathematically.

What is the difference between type I and type II errors?

Type I and II Errors

How would you tackle multicollinearity in multiple linear regression?

Multicollinearity in Regression

What does the backpropagation algorithm do in the context of neural networks? What is the informal intuition behind the algorithm? What are some drawbacks of the algorithm compared to other optimization methods?

Bonus: Formally derive the backpropagation algorithm and prove that it does what it claims to do.

Backpropagation Explanation

Given a <code>employees</code> and <code>departments</code> table, select the top 3 departments with at least ten employees and rank them according to the percentage of their employees making over 100K in salary.

Example:

Input:

<code>employees</code> table

<table>
<thead>
<tr>
<th>Columns</th>
<th>Type</th>
</tr>
</thead>

<tbody>
<tr>
<td><code>id</code></td>
<td>INTEGER</td>
</tr>

<tr>
<td><code>first_name</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>last_name</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>salary</code></td>
<td>INTEGER</td>
</tr>

<tr>
<td><code>department_id</code></td>
<td>INTEGER</td>
</tr>
</tbody>
</table>
<code>departments</code> table

<table>
<thead>
<tr>
<th>Columns</th>
<th>Type</th>
</tr>
</thead>

<tbody>
<tr>
<td><code>id</code></td>
<td>INTEGER</td>
</tr>

<tr>
<td><code>name</code></td>
<td>VARCHAR</td>
</tr>
</tbody>
</table>
Output:

<table>
<thead>
<tr>
<th>Column</th>
<th>Type</th>
</tr>
</thead>

<tbody>
<tr>
<td><code>percentage_over_100k</code></td>
<td>FLOAT</td>
</tr>

<tr>
<td><code>department_name</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>number_of_employees</code></td>
<td>INTEGER</td>
</tr>
</tbody>
</table>

How would you explain the concept of linear regression to three different audiences: a child, a first-year college student, and a seasoned mathematician? Ensure your explanations are tailored to the understanding level of each audience.

Implement the k-means clustering algorithm in python from scratch, given the following:

<ul>
<li>A two-dimensional NumPy array <code>data_points</code> that is an arbitrary number of data points (rows) <code>n</code> and an arbitrary number of columns <code>m</code>.</li>
<li>Number of k clusters <code>k</code>.</li>
<li>The initial centroids value of the data points at each cluster <code>initial_centroids</code>.</li>
</ul>

Return a list of the cluster of each point in the original list data_points with the same order (as a integer).

Example

<img src="https://i.ibb.co/KKp2gPn/kemans-before.png" alt="before clustering"/>

After clustering the points with two clusters, the points will be clustered as follows.

<img src="https://i.ibb.co/bdwVWxR/kemans-example-after.png" alt="after clustering"/>

Note: There could be an infinite number of separating lines in this example.

Example

<pre tabindex="0" class="chroma"><code>
#Input
data_points = [(0,0),(3,4),(4,4),(1,0),(0,1),(4,3)]
k = 2
initial_centroids = [(1,1),(4,5)]


#Output 

k_means_clustering(data_points,k,initial_centroids) -&gt; [0,1,1,0,0,1]

</code></pre>

<img src="https://i.ibb.co/pRsRz12/example.png" alt=""/>

Implement the k-means clustering algorithm in python from scratch

k-Means from Scratch

Let’s say you have a categorical variable with thousands of distinct values, how would you encode it?

Which method can be used to extract communities from large networks, that does not require a pre-determined number of clusters like K-means?

Which method can be used to extract communities from large networks, that does not require a pre-determined number of clusters like K-means?

Let’s say that you’re a data scientist at DoorDash.

How would you build a model to predict which merchants the company should go after for acquisition when entering a new market?

We want to determine if Uber Eats has a net positive value for the company Uber.

How would you measure the success of Uber Eats?

If Uber wants to evaluate the customer loyalty and repeat business on Uber Eats, which of the following metrics would be the most relevant?

If Uber wants to evaluate the customer loyalty and repeat business on Uber Eats, which of the following metrics would be the most relevant?

Uber Eats Success I

Which among the following metrics would be most indicative of the operational efficiency of Uber Eats?

Which among the following metrics would be most indicative of the operational efficiency of Uber Eats?

Uber Eats Success II

Which among the following metrics would be most critical in evaluating the overall profitability of Uber Eats for Uber?

Which among the following metrics would be most critical in evaluating the overall profitability of Uber Eats for Uber?

Uber Eats Success III

Uber Eats Success

Product Sense & Metrics

What are the benefits of dynamic pricing, and how can you estimate supply and demand in this context?

Achieving maximum profits through dynamic pricing with real-time supply and demand fluctuations

Understanding Dynamic Pricing Strategy

Let’s say you work at a food delivery company.

How would you measure the effectiveness of giving extra pay to delivery drivers during peak hours to meet the demand from consumers?

Extra Delivery Pay

To improve customer experience on Uber Eats, what key parameters would you focus on improving?

Delivering an exceptional customer experience by focusing on key customer-centric parameters

Uber Eats Customer Experience

One day you are invited to your kid’s kindergarten. The children there ask about your work as a machine learning engineer.

How would you explain neural networks to the kids there?

Explain Neural Nets to Kids

Write a function to get a sample from a standard normal distribution.

Write a function to get a sample from a standard normal distribution.

Normal Distribution Sample

Probability

How would you build the recommendation algorithm for type-ahead search for Netflix?

You work as a data scientist on a ride sharing marketplace.

<ol>
<li>What metrics would you look at to determine the demand for rides at any point?</li>

<li>What metrics would tell you if there is high demand and low supply? How can you determine the threshold for when there’s too much demand?</li>
</ol>

As a data scientist in a ride sharing marketplace, which metrics could help determine the demand for rides at any point?

As a data scientist in a ride sharing marketplace, which metrics could help determine the demand for rides at any point?

Demand Metrics I

In the context of a ride sharing marketplace, which situation would indicate a high demand and low supply?

In the context of a ride sharing marketplace, which situation would indicate a high demand and low supply?

Demand Metrics II

How would you identify supply and demand mismatch in a ride sharing market place?

Demand Metrics

Let’s say we want to build a model to predict the time spent for a restaurant to prepare food from the moment an order comes in until the order is ready. 

What kind of model would we build and what features would we use?

Let’s say you’re working on DoorDash demand side deliveries. DoorDash is launching delivery services in New York City and Charlotte and needs a process for selecting dashers (delivery drivers).

Let’s say we want to create a model to determine which Dashers should deliver a particular order.

We currently have these features already in our model.

<ul>
<li>Dasher distance to the restaurant</li>
<li>Number of Dasher reviews from customers</li>
<li>Number of Dasher successful deliveries</li>
</ul>

Which feature would be the best additional input to our existing features to improve the model?

Let's say you're working on DoorDash demand side deliveries. DoorDash is launching delivery services in New York City and Charlotte and needs a process for selecting dashers (delivery drivers).

Let's say we want to create a model to determine which Dashers should deliver a particular order.

We currently have these features already in our model. 

- Dasher distance to the restaurant
- Number of Dasher reviews from customers
- Number of Dasher successful deliveries

Which feature would be the best additional input to our existing features to improve the model?



Dasher Model

Given an array of <code>words</code> and a <code>max_width</code> parameter, write a function <code>justify</code> to format the text such that each line has exactly <code>max_width</code> characters. Pad extra spaces ’ ‘ when necessary so that each line has exactly <code>max_width</code> characters.

Extra spaces between words should be distributed as evenly as possible. If the number of spaces on a line does not divide evenly between words, place excess spaces on the right-hand side of each line.

Note: You may assume that there is no word in <code>words</code> that is longer than <code>max_width</code>.

Example:

Input:

<pre tabindex="0" class="chroma"><code>words = [&#34;This&#34;, &#34;is&#34;, &#34;an&#34;, &#34;example&#34;, &#34;of&#34;, &#34;text&#34;, &#34;justification.&#34;]
max_width = 16

def justify(words, max_width): -&gt;
[
 &#34;This is an&#34;,
 &#34;example of text&#34;,
 &#34;justification. &#34;
]
</code></pre>

Let’s say that you’re working on the Uber app. 

How would you design an incentive scheme for drivers such that they would more likely go into city areas where demand is high?

Challenge

Joby Aviation Salaries by Position

<h5>Senior Software Engineer - Microsoft Dynamics 365 Finance and Operations </h5>This is your chance to directly impact mission-critical business processes across Finance, Supply Chain, and Manufacturing. As a key technical leader, you will be instrumental in designing, enhancing, and maintaining our Microsoft Dynamics 365 Finance and Operations (D365 F&O) platform. Your work will ensure the system is optimized, integrated, and aligned with the company's growth trajectory and operational needs. You will act as a senior technical advisor on D365 F&O architecture, development best practices, and integration strategies. We're looking for someone who can derive, design, and continuously improve the overall D365 F&O ecosystem. <h5>Responsibilities </h5><ol> <li>Derive, design, and continuously improve the overall D365 F&O platform architecture, focusing on performance, scalability, and maintainability. </li><li>Develop, customize, and extend D365 F&O applications using X++ and C# to support complex Finance, Supply Chain, and Manufacturing business requirements. </li><li>Integrate D365 F&O with the broader enterprise system landscape (e.g., PLM, MES, CRM) using D365 APIs, Data Management Framework (DMF), Dataverse, Power Platform, Azure Logic Apps, and other Azure services. </li><li>Provide senior-level technical support, troubleshooting, and performance optimization for D365 F&O environments and custom solutions. </li><li>Analyze complex business workflows across departments (e.g., GL, AP, Inventory) to identify opportunities for system automation and efficiency improvements within D365 F&O. </li><li>Collaborate closely with international, cross-functional teams (Functional Consultants, Business Analysts, IT) to ensure effective delivery and adoption of D365 F&O solutions. </li><li>Act as a senior technical advisor on D365 F&O architecture, implementation methodologies, and best practices for module configuration and customization. </li><li>Lead strategic initiatives, including system upgrades, application of new D365 F&O feature sets, and migration strategies to enhance the business technology stack. </li></ol> <h5>Required </h5><ul> <li>Bachelor's degree in Software Engineering, Computer Science, or a comparable technical field. </li><li>5+ years of technical experience with Microsoft Dynamics 365 Finance and Operations (or Dynamics AX 2012). This includes, but not limited to, implementations, customizations, and integrations. </li><li>Strong programming skills in X++ and C#; experience with the D365 F&O development stack and tools. </li><li>Deep understanding of D365 F&O integration patterns, including OData, custom services, Data Management Framework (DMF), and event-driven architectures (e.g., Azure Service Bus/Event Hub). </li><li>Solid knowledge of the underlying D365 F&O architecture, Life Cycle Services (LCS), and best practices for cloud-based ERP deployments. </li><li>Proven expertise in customizing and extending at least three core D365 F&O modules (e.g., General Ledger, Accounts Payable, Inventory Management, Production Control, or Project Accounting). </li><li>Excellent problem-solving skills, proactive mindset, and ability to work effectively in global teams. </li><li>Experience with standard software development practices, including Agile methodologies, CI/CD pipelines, and Git-based workflows (preferably Azure DevOps). </li></ul> <h5>Desired </h5><ul> <li>Background in aerospace, automotive, complex manufacturing, or another highly regulated industry. </li><li>Previous experience in startups or high-growth environments, particularly with a global D365 F&O rollout. </li><li>Proficiency in related Microsoft technologies, such as Power Platform (Power BI, Power Apps) and Azure services. </li><li>Proven track record of delivering end-to-end ERP solutions, from initial design through development, testing, deployment, and post-go-live support. </li></ul> Please still apply if you don't meet all items in the desired section! Studies have shown that women and people of color are less likely to apply to jobs unless they meet every single qualification. We are dedicated to building a diverse and effective workplace, so if you're excited about this role but your experience doesn't align perfectly with every qualification, we encourage you to apply anyway. You may be just the right candidate for this or other roles. <h5>Additional Information </h5>Compensation at Joby is a combination of base pay, bonus, and Restricted Stock Units (RSUs). The target base pay for this position is $116,500 - $178,600 per year. The compensation package offered will be determined by location, job-related knowledge, skills, and experience. Joby also offers a comprehensive benefits package, including paid time off, healthcare benefits, a 401(k) plan with a company match, an employee stock purchase plan (ESPP), short-term and long-term disability coverage, life insurance, and more. Joby is an Equal Opportunity Employer.

<h5>Senior Software Engineer 3DX </h5>Imagine a piloted air taxi that takes off vertically, then quietly carries you and your fellow passengers over the congested city streets below, enabling you to spend more time with the people and places that matter most. Since 2009, our team has worked steadily to make this dream a reality. We're looking for talented, committed individuals to join our team as we push onward toward certifying the Joby aircraft, scaling our manufacturing, and launching our initial commercial service. This is your chance to directly impact the mission of certifying the Joby aircraft and scaling our manufacturing operations. As the technological backbone of Joby's operations, the Factory Systems team plays a crucial role in engineering, manufacturing, quality, and more. You'll be instrumental in designing and enhancing our Product Lifecycle Management (PLM) system, which will optimize the experience for our design engineers and other users. Your work will be at the forefront of virtual product development and digital twin integration. You'll act as a senior technical advisor on PLM, modeling, and simulation strategies using the 3DEXPERIENCE platform (including CATIA, ENOVIA, and DELMIA). We're looking for someone who can derive, design, and continuously improve the overall 3DX platform architecture. <h5>Responsibilities </h5><ul> <li>Derive, design, and continuously improve the overall 3DX platform architecture </li><li>Act as a senior technical advisor on PLM, modeling, simulation, and configuration management strategies using 3DEXPERIENCE (CATIA, ENOVIA, DELMIA) </li><li>Implement and extend applications within the 3DX platform to support business and engineering needs </li><li>Integrate 3DX into the broader system landscape through APIs and custom services, ensuring seamless connectivity with ERP, MES, and QMS systems </li><li>Provide technical support, troubleshooting, and performance optimization for 3DX solutions </li><li>Analyze engineering and business workflows to identify opportunities for automation and efficiency improvements </li><li>Collaborate closely with an international, cross-functional team to ensure effective delivery and adoption of 3DX solutions </li><li>Lead strategic initiatives in virtual product development, digital twin/digital thread integration, and model-based engineering </li><li>Collaborate with product teams and industry partners to define best practices and drive adoption of advanced PLM and design methodologies </li></ul> <h5>Required </h5><ul> <li>Bachelor's degree in Software Engineering, Mechanical Engineering, or a comparable field </li><li>5+ years of software engineering experience within the 3DX platform, specifically CATIA, DELMIA, or ENOVIA </li><li>Strong programming skills in Java; Python is a plus </li><li>Deep understanding of APIs, web services, and event-based processing (e.g., Kafka or similar technologies) </li><li>Solid knowledge of the underlying architecture and infrastructure of an on-premise 3DX implementation </li><li>Excellent problem-solving skills, proactive mindset, and ability to work effectively in global teams </li><li>Experience with standard software development practices, including CI/CD and Git-based workflows </li></ul> <h5>Desired </h5><ul> <li>Background in aerospace, automotive, or other design/manufacturing industries </li><li>Previous experience in startups or high-growth environments </li><li>Proven track record of delivering end-to-end solutions, from product development through to support </li></ul> Please still apply if you don't meet all items in the desired section! Studies have shown that women and people of color are less likely to apply to jobs unless they meet every single qualification. We are dedicated to building a diverse and effective workplace, so if you're excited about this role but your experience doesn't align perfectly with every qualification, we encourage you to apply anyway. You may be just the right candidate for this or other roles. <h5>Additional Information </h5>Compensation at Joby is a combination of base pay, bonus, and Restricted Stock Units (RSUs). The target base pay for this position is $116,500 - $178,600/year. The compensation package offered will be determined by location, job-related knowledge, skills, and experience. Joby also offers a comprehensive benefits package, including paid time off, healthcare benefits, a 401(k) plan with a company match, an employee stock purchase plan (ESPP), short-term and long-term disability coverage, life insurance, and more. Joby is an Equal Opportunity Employer.

A leading aerospace firm in California is seeking a Senior Embedded Software Engineer to develop cutting-edge flight automation systems. This role involves contributing to the software architecture, designing simulation tools, and integrating embedded software. Ideal candidates should have a strong grasp of programming languages such as C, C++, and Python, along with experience in safety-critical software systems. The position offers competitive salary and comprehensive benefits, making it an appealing opportunity for qualified individuals.
 #J-18808-Ljbffr

Calculate Moving Average	SQL	Easy
Predict Customer Churn	Machine Learning	Medium
A/B Test Significance	Statistics	Medium
Optimize Query Performance	SQL	Hard
Feature Importance Analysis	Machine Learning	Medium
Clean Missing Data	Python	Easy
Neural Network Architecture	Deep Learning	Hard
Calculate Cohort Retention	SQL	Medium
Bayesian Probability	Statistics	Easy
Recommend Similar Products	Machine Learning	Hard

Joby Aviation Interview Questions

Joby Aviation Interview Guides