2027 Summer Intern, PhD, Research, Behavior Post-training
Core
Develop machine learning solutions for autonomous driving using synthetic data and post-training methods.
Role type
PhD Research Intern (Autonomous Driving / Reinforcement Learning)
Builds
Tools for sampling synthetic driving data and models trained on mixtures of synthetic and logged data.
Domain
Autonomous driving, Machine Learning, Robotics
Deliverable
production ML models
Required skills
Sampling from large models, Post-training methods (SFT, RL, preferences), Modern deep learning frameworks (PyTorch, Jax)
Preferred skills
Open/closed loop decision making in robotics, Synthetic data generation and evaluation, LLM-as-a-judge
Technologies
PyTorch, Jax
Responsibilities
Build tools for sampling, selecting, and discarding synthetic driving data; Train and evaluate models with mixtures of synthetic and logged data; Present and write about methods for synthetic data generation and training
Seniority
Intern