We are hiring a Research Engineer to advance our models’ ability to safely write correct, fast code for accelerators within Anthropic’s Code RL team. The role involves inventing, designing and implementing RL environments and evaluations, conducting experiments, shaping research roadmap, delivering work into training runs, and collaborating across research, engineering and performance engineering teams.
Research Engineer, Performance RL (Reinforcement Learning) at Anthropic
Hybrid - San Francisco, CA
More jobs at AnthropicSalary
USD 350,000 - 850,000
Requirements
Skills
- Expertise with accelerators (CUDA, ROCm, Triton, Pallas)
- ML framework programming (JAX or PyTorch)
- Experience across the stack – kernels, model code, distributed systems
- Ability to balance research exploration with engineering implementation
- Passion for AI safety and benefit
- Experience with reinforcement learning
- Experience porting ML workloads between different types of accelerators
- Familiarity with LLM training methodologies
- Bachelor’s degree or equivalent combination of education, training, and/or experience
Responsibilities
- Invent, design and implement RL environments and evaluations
- Conduct experiments and shape the research roadmap
- Deliver work into training runs
- Collaborate with researchers, engineers, and performance engineering specialists across and outside Anthropic
Technologies
CUDAROCmTritonPallasJAXPyTorchReinforcement learningDistributed systems
See if your resume is ready for this job
See how our AI can optimize your resume and improve your chances for this role.