About the role#
This PhD research internship focuses on the intersection of reinforcement learning and large language models. You will join the applied deep learning research team to design, implement, and evaluate new methods aimed at improving the reasoning, alignment, and reliability of foundation models. The role emphasizes hands-on experimentation and rapid prototyping at scale.
What you'll do#
- Develop and prototype reinforcement learning algorithms for large language models.
- Explore methods to enhance reasoning, instruction following, multi-turn interaction, and alignment.
- Design experiments to evaluate model robustness, task performance, and hallucination.
- Implement research ideas using Python and PyTorch, running experiments on large-scale GPU clusters.
What you'll need#
- Currently pursuing a PhD in AI, Machine Learning, Computer Science, Computer Engineering, Electrical Engineering, Mathematics, Physics, or a related field.
- Strong background in reinforcement learning and natural language processing.
- Excellent programming skills, specifically in Python.
- Experience with deep learning frameworks, particularly PyTorch.
- Comfort with experimental research, debugging models, and working with large-scale training pipelines.
- Bonus qualifications include publications or open-source contributions in RL, LLMs, alignment, or reasoning, as well as experience with RLHF, RLAIF, policy optimization, reward modeling, or agentic systems.
Location & details#
- Location: Santa Clara, California, United States.
- Term: Fall 2026.
- Modality: On-site.
- Status: Full-time internship.
- Compensation: 30 USD - 94 USD per hour, dependent on location, education, and experience.
