2026 Summer Intern, Machine Learning Engineer, Trajectory Generation (PhD)

Job Description

To help facilitate administration of relocation benefits if you are selected, please apply using the permanent address you would move from. 

Work Arrangement: 
Hybrid: This internship is categorized as hybrid. The selected intern is expected to report to the office up to three times per week or as determined by the team. 

Locations:  

• San Francisco, California 

• Sunnyvale, California  

• Mountain View, California 

About the Team:  

The trajectory generation team (TGX) is responsible for turning scene understanding into wholistic AV behavior. The team must balance multiple competing objectives. Trajectories need to be comfortable for passengers (minimizing jerk and acceleration), obey traffic laws, respect vehicle dynamics constraints (steering limits, acceleration capabilities), avoid obstacles, and respond in real-time to changing road conditions. The TGX team uses state-of-the-art ML, RL, and optimization techniques to improve the GM driving product and support the objectives above. 

About The Role:  

As an intern on the trajectory generation team, you would work on well-scoped research or engineering projects that contribute to the team's ML-driven planning stack. This might involve implementing and benchmarking new neural network architectures for behavior prediction, improving data pipelines for training trajectory models, or conducting ablation studies on different learning approaches. The intern would collaborate closely with senior engineers and researchers, participating in code reviews, team meetings, and design discussions while gaining hands-on experience with production autonomous driving systems. They'd work with real-world driving data, simulation environments, and potentially see their contributions deployed to test vehicles. 

The role offers a unique opportunity to bridge cutting-edge ML research with safety-critical robotics applications. An intern would develop skills in deep learning frameworks (PyTorch), work with large-scale distributed training systems, and learn how to validate and verify learned models for autonomous driving. Beyond technical skills, they'd gain insight into the challenges of building reliable AI systems for the real world—handling edge cases, ensuring safety guarantees, and balancing model performance with computational constraints. The experience provides exposure to how ML teams operate within a complex, multi-disciplinary engineering organization building toward full autonomy. 

What You’ll Do:  

• Implement and experiment with neural network architectures for trajectory prediction, behavior planning, or mission planning tasks 

• Build data pipelines and visualization tools to process, analyze, and evaluate large-scale driving datasets 

• Train and benchmark ML models using distributed compute infrastructure, running ablation studies to optimize performance 

• Validate models in simulation environments and analyze failure cases across diverse driving scenarios