PhD Research Intern, Simulation/ML

Internship Program:

Stack is revolutionizing transportation through AI and is seeking the best and brightest interns to help us realize this vision! As an early-stage start up, we expect our interns to be an integral part of the team, working on robotics research projects that directly impact our product. Along the way, you’ll be provided with opportunities for collaboration and mentorship with industry leaders to accelerate your career and research goals. 

We welcome students who are enrolled in university, pursuing a doctorate degree and are currently located in the United States. Summer internships are typically 12 weeks in duration (note: we may be flexible for internships to start in the spring semester or continue into the fall semester).

We offer competitive pay and support sponsorship.

About the Team:

The Autonomy Evaluation Team is a group of specialized engineers dedicated to developing simulation tools and metrics pipelines. The simulation tools include log-based simulation and synthetic simulation, which simulates sensors and intermediate values such as nearby actors, map data and vehicle state. Our metrics pipelines evaluate the results of simulations as well as vehicle logs, enabling data mining, performance evaluation and identification of critical errors.

The Decision Making Machine Learning team is responsible for designing, building, and deploying machine learning systems within our prediction and motion planning components. We work with state-of-the-art algorithms and large amounts of data to elegantly capture complex behavior and solve difficult situations to improve our truck’s autonomous driving capabilities.

Research Areas:

The project work will be scoped specifically based on your skill set and the research needs of the team, but project areas could include…

• Example project #1: Optimized Traffic/Actor Generation (Sim / ML Team)- Work with adjacent systems and safety teams to understand the operating environment for an AV and develop scenarios with generated actors to fully cover the possible AV-actor interactions.  Actors may include vehicles, static objects and VRUs.


• Example project #2: Sensor Simulation - Novel View Generation (Sim / ML)- Develop methods to work with sensor data from logs to generate novel views that can be used to output altered sensor data from nearby but previously untraveled vehicle positions.


• Example project #3: Sensor Simulation - Sensors From Scene Data (Sim)- Develop methods to utilize intermediate system outputs such as mapping information, lane lines, actor information and obstacle information to generate corresponding synthetic sensor data such as camera imagery and LIDAR points.


• Example Project #4 - Scene Prediction (ML)- Work with existing datasets to predict joint future trajectories for all actors in a scene in order to understand driving dynamics and guide AV behavior in reaction to agent predictions.

In order to be considered for this team, we strongly encourage students to have the following skills and experiences…

• Python and C++ programming languages


• Simulation tooling execution and development


• Machine learning / Reinforcement learning experience


• Sensor generation and transformation experience (camera, LIDAR)


• Cross functional communication skills


• Software engineering best practices


• Test driven development experience