2027 Summer Intern, Onboard Autonomy, Embodied AI
About The Position
The Onboard Autonomy team develops the real-time intelligence that enables autonomous vehicles to perceive their surroundings, plan safe and comfortable behavior, and operate reliably on the vehicle. Our work spans sensor fusion, structured perception, trajectory generation, ML planning, local planning, controls, guardrails, evaluation, and vehicle integration. We combine machine learning, robotics, optimization, and software engineering to build production-oriented autonomy systems that operate in real time and handle challenging driving scenarios. As an Onboard Autonomy Intern, you will contribute to a focused research or engineering project within the onboard driving stack. You will work with experienced researchers and engineers to prototype, evaluate, and improve algorithms or software using vehicle data, simulation, or production-oriented environments. Potential focus areas include: Sensor Encoders and Fusion: Convert camera, lidar, radar, and other sensor inputs into useful representations for autonomy. Structured Perception: Improve object tracking, online maps, scene understanding, and long-tail scenario handling. ML Planning and Trajectory Generation: Predict behavior, generate trajectories, and select safe driving actions. Local Planning and Controls: Balance collision avoidance, traffic rules, vehicle dynamics, kinematic feasibility, and passenger comfort. Guardrails and Integration: Validate and integrate autonomy components across vehicle platforms to support safe, reliable operation.
Requirements
- Currently pursuing a Master’s or Ph.D. in Computer Science, Robotics, Electrical or Mechanical Engineering, Controls, Machine Learning, or a related STEM field.
- Experience through coursework, research, projects, or professional work in machine learning, computer vision, robotics, controls, optimization, or autonomous systems.
- Strong Python skills and experience with C++ or another systems programming language.
- Strong analytical, problem-solving, communication, and collaboration skills.
- Availability to work full-time, 40 hours per week, during the internship.
Nice To Haves
- Experience with autonomous vehicles, ADAS, robotics, or ROS.
- Experience with PyTorch, TensorFlow, JAX, deep learning, transformers, multimodal learning, reinforcement learning, imitation learning, or trajectory prediction.
- Background in vehicle dynamics, feedback control, trajectory optimization, motion planning, safety-critical software, simulation, closed-loop evaluation, sensor data, large-scale datasets, or distributed computing.
- Intent to return to a degree program after the internship or co-op.
- Must be graduating between December 2027 and June 2028
Responsibilities
- Prototype and evaluate algorithms for perception, prediction, planning, trajectory generation, controls, or integration.
- Work with real-world driving data and simulation to measure performance and investigate failures.
- Build data-processing, visualization, testing, and evaluation tools.
- Contribute to production-quality software through design reviews, code reviews, automated testing, continuous integration, and documentation.
- Analyze results, improve system performance, collaborate across disciplines, and present technical findings.
Benefits
- Paid U.S. GM holidays.
- GM Family First Vehicle Discount Program.
- Potential for growth within GM based on performance and business needs.
- Intern events and opportunities to network with company leaders and peers.
- Mentorship and hands-on experience with the data and ML foundations behind autonomy
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Intern
