Summer 2027 Master's AI Research, Reinforcement Learning and LLM Post-Training Intern
Core
Research and prototype reinforcement learning methods for post-training language and code models, focusing on policy optimization, reward modeling, and failure analysis.
Role type
Master's level AI research intern (RL and LLM post-training)
Builds
Post-training methods for language and code models
Domain
Artificial Intelligence / Machine Learning
Deliverable
production ML models
Required skills
Reinforcement learning, deep learning, Python, PyTorch, LLM post-training, RLHF/RLAIF, preference optimization, reproducible experiments
Preferred skills
Publications at top ML conferences, GPU computing, distributed training, compilers, kernels, optimization
Technologies
Python, PyTorch
Responsibilities
Research and prototype RL methods for post-training; Explore policy optimization and reward modeling; Design and run controlled experiments; Analyze failure modes like reward hacking; Develop evaluation methods; Collaborate on rollout generation and training; Document findings and contribute to publications
