Research Engineer/Research Scientist, RL/Reasoning
Advances AI capabilities through cutting-edge reinforcement learning research, training intelligent agents for models like o1 and o3. Requires RL research background, strong coding skills, and ability to iterate quickly in a fast-paced environment.
About the job
Responsibilities
- Advance the frontier of AI alignment and capabilities through cutting-edge RL methods.
- Work at the heart of training intelligent, aligned, and general-purpose agents, including systems powering various models.
Requirements
- Background in reinforcement learning research.
- Ability to iterate quickly.
- Proficient at coding.
- Comfortable diving into a large ML codebase to debug and improve it.
- Deep understanding of machine learning and ML applications.
Nice-to-haves
- Love being on the cutting edge of RL and language model research.
- Self-starter who takes initiative and ownership of ideas.
- Value principled approaches, simple experiments, and trustworthy conclusions.
- Thrive in fast-paced, dynamic, technically complex environments with rapid iteration.
Skills
Reinforcement Learning, PyTorch, Machine Learning, Language Models, Generative Models, Deep Learning, Ai Alignment, JAX, Computational Optimization
Similar jobs
AI Research jobs
OpenAI
San Francisco, CA
Conducts frontier AI research for health, developing and evaluating scalable training methods, models, and agents that improve medical reasoning, reliability, and real-world outcomes. Requires exceptional machine learning or biomedical AI research depth, hands-on coding and experimentation, and end-to-end ownership of ambiguous problems.
Anthropic
San Francisco, CA
Conducts hands-on medicinal chemistry research to evaluate AI-generated molecules and synthetic routes, advancing small-molecule programs from design through experimental validation. Requires a chemistry PhD, sustained synthetic experience, and cross-functional collaboration skills.
Descript
San Francisco, CA
Applied research scientists develop deep-learning and generative media systems for video, audio, and multimodal editing features that ship to millions of users. The role requires strong PyTorch or TensorFlow skills, rapid experimentation, and evidence of impactful research or production machine-learning work.
The Voleon Group
New York, NYConducts causal inference research for financial market prediction and portfolio optimization, developing and validating models from research through live trading. Requires Ph.D.-level coursework, strong causal inference and statistics expertise, mathematical ability, and production Python skills.
Anthropic
San Francisco, CA
Research Engineer building large-scale AI capability evaluations, telemetry, data pipelines, and analysis tools for Anthropic’s Takeoff Intel team. The role requires hands-on large language model experimentation, rapid prototyping, data expertise, and strong research collaboration.