Research Scientist - Reinforcement Learning
$150k - $450k • Sunnyvale, CA • Full-time
Posted 1y ago
Job Location
Sunnyvale, CA
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Research Engineer
About the job
The Institute of Foundation Models is a research lab focused on building, understanding, using, and managing foundation models. We aim to advance AI research, cultivate future AI leaders, and drive innovation in the knowledge economy. As a Research Scientist in Reinforcement Learning, you will be instrumental in shaping the scientific and technical direction for developing emergent capabilities within Foundation Models. This role involves pioneering novel Reinforcement Learning approaches, prototyping new learning methods, contributing to large-scale RL training infrastructure, and producing high-quality, replicable code for public release. You will also build and maintain a research portfolio through collaborations.
Responsibilities
- Develop novel research for large-scale self-play in foundation model training, agentic tasks, and enabling models to learn proactively from their environment.
- Initiate and pursue new reinforcement learning algorithmic approaches to define and drive emergent capabilities in Foundation Models.
- Perform full-stack engineering, including data curation, model architecture and algorithm design, and production of models using well-documented, tested, and maintainable code.
- Contribute to technical reports and research publications.
- Represent the institution at industry conferences and events to showcase technology and establish leadership in AI research.
- Proactively engage with the open-source community.
- Contribute to large-scale reinforcement learning training and inference frameworks.
- Facilitate internal and external collaborations.
Requirements
- MSc/MEng or PhD Degree (or equivalent experience) in Machine Learning, Computer Science, or related fields.
- Minimum of 3 years of hands-on experience with reinforcement learning.
- Demonstrated ability to identify limitations in current practices and formulate/execute improvement strategies independently.
- Proactive mindset with the ability to identify impactful research questions and execute them with minimal supervision.
- Strong Python development skills with a focus on research-grade code and scalable data pipelines.
- Practical experience implementing complex mathematical concepts into reliable, well-documented code.
- Experience applying novel RL algorithms to practical applications.
- Strong experience contributing to academic and/or open-source research through publications, GitHub contributions, or presentations.
- Strong communication and collaboration skills for effective cross-functional work.
- Strong systems and engineering expertise in deep learning frameworks such as PyTorch, Jax, etc.
- Experience in large-scale model training (LLMs or Diffusion Models) on large clusters.
- Familiarity with current RL+LLM training libraries.
- Experience training policies in self-play.
- Experience working with Diffusion Models in RL.
- Strong publication record in leading AI and RL venues (e.g., ICLR, ICML, NeurIPS, RLC, JMLR, TMLR).
- Familiarity with performance constraints in production environments and trade-offs in model design and execution.
- Prior contributions to open-source ML research or data tools.
- Demonstrated ability to solve complex system-level challenges and debug failures across the training/inference stack.