Research Scientist
Research Scientist responsible for measuring and improving how frontier models learn from tasks, designing post-training experiments, validating data quality, and creating datasets and evaluation systems. Requires production reinforcement-learning experience at a frontier lab and end-to-end LLM post-training experience.
About the job
Responsibilities
- Collaborate with researchers at frontier labs to design novel post-training recipes and data-quality measurement techniques.
- Design and run the in-house post-training stack to measure model lift on tasks.
- Develop new data products from available datasets and experts.
- Work with procurement to assess external data for refinement.
- Build scalable systems for ingesting and evaluating prospective data purchases.
Requirements
- At least 1 year of experience doing reinforcement learning in production at a frontier lab.
- Track record of post-training a large language model end to end.
- Experience validating data quality and identifying opportunities for improvement.
- Ability and desire to drive the research roadmap and implementation on a fast-moving team.
- Deep curiosity about how machines learn from data and how to extract maximum learning signal from tasks.
Technical Stack
- TypeScript
- React
- Node.js
- PostgreSQL
- Redis
- Vercel
- Cursor
Compensation and Benefits
- Competitive salary and meaningful equity.
- Free meals in the office.
- Healthcare.
- 401(k).
- 15 days of paid time off per year.
- Relocation assistance.
Skills
Reinforcement Learning, Post-Training, LLMs, TypeScript, React, Node.js, Postgres, Redis, Vercel, Cursor
Similar jobs
AI Research jobs
Immuta
College Park, MD
Summer 2027 internship applying computer science, mathematics, statistics, and machine learning research to practical product capabilities. The intern will prototype, evaluate, and communicate solutions involving data privacy, security, governance, algorithms, and text analytics.
Fireworks AI
San Mateo, CAConduct foundational research on LLMs and multimodal systems, designing architectures and training methods and helping move prototypes into production. The role targets PhD researchers graduating by December 2026 with strong machine-learning research and programming experience.
OnePay
United States
AI Research Intern researching agentic AI applications for customer-facing products and developing working prototypes. The role requires current pursuit of a technical bachelor's degree, prior software engineering or substantial project experience, and interest in LLMs or generative AI.
Replit
Foster City, CA
Paid internship for quantitative students contributing to AI-powered software creation, systems optimization, and developer tooling. Candidates should demonstrate strong mathematical ability, curiosity about AI, and autonomous cross-functional collaboration.
OpenAI
San Francisco, CA
Researcher developing and publishing mechanistic interpretability techniques, building infrastructure to study model internals, and guiding alignment-focused research. Requires research experience in machine learning or a related field, strong engineering skills, and proficiency in Python or similar languages.