Reinforcement Learning Research Engineer — Safe AI Code

SignalAI; San Francisco (CA); Hybrid; USD 350,000 - 850,000; Full time

Benefits offered by this job

Equity donation matching

Generous vacation & parental leave

Flexible working hours

Office in San Francisco

Job summary

Anthropic is hiring for the Code RL team within the RL organization. As a Research Engineer, you'll advance our models' ability to safely write correct, fast code for accelerators.

You’ll Need To Know Accelerator Performance Well To Turn It Into Tasks And Signals Models Can Learn From. Specifically, You Will Invent, design and implement RL environments and evaluations, conduct experiments and shape our research roadmap, deliver your work into training runs, and collaborate with other

Qualifications

• Experience with accelerators (CUDA, ROCm, Triton, Pallas).
• Experience with ML frameworks (JAX or PyTorch).
• Experience across kernels, model code, and distributed systems.

Responsibilities

• Invent, design and implement RL environments and evaluations.
• Conduct experiments and shape our research roadmap.
• Deliver your work into training runs.
• Collaborate with other researchers, engineers, and performance engineering specialists across and outside Anthropic.

Skills

Accelerators

ML frameworks

Code & kernel stacks

Distributed systems

Research to engineering balance

Education

Bachelor’s degree

Job description

Anthropic is hiring for the Code RL team within the RL organization. As a Research Engineer, you'll advance our models' ability to safely write correct, fast code for accelerators.

You’ll Need To Know Accelerator Performance Well To Turn It Into Tasks And Signals Models Can Learn From. Specifically, You Will Invent, design and implement RL environments and evaluations, conduct experiments and shape our research roadmap, deliver your work into training runs, and collaborate with other