Summer 2027 PhD Gen AI and Reinforcement Learning Research Intern
Core
Research and prototype methods for post-training large generative models, focusing on policy optimization, preference learning, reward modeling, and agentic behavior.
Role type
PhD Research Intern (Gen AI & Reinforcement Learning)
Builds
Research prototypes and technical reports for large generative models
Domain
Artificial Intelligence / Machine Learning
Deliverable
research
Required skills
Reinforcement learning, Deep learning, Python, PyTorch, LLM post-training, RLHF/RLAIF, Preference optimization, Agentic systems, Experimental design, Model evaluation
Preferred skills
Publications at top ML conferences, Large-scale model training, GPU computing, Distributed systems, Multimodal learning, Reasoning models
Technologies
Python, PyTorch, LLMs, GPUs
Responsibilities
Research and prototype post-training methods for large generative models; Explore policy optimization and reward modeling; Develop methods for reasoning and agentic behavior; Design and run controlled experiments; Analyze failure modes like reward hacking; Develop evaluations for model quality and safety; Collaborate on training and reproducibility; Document findings and contribute to publications.
