Research Engineer, Performance RL (Reinforcement Learning)

Anthropic
San Francisco
Workplace: OnsiteFull timeFunction: Research & Scientific (R&D)Education: bachelorsSkills: ["Communication","Problem-solving","Teamwork"]

Join the Code RL team as a Research Engineer, advancing models’ ability to safely write correct, fast code for accelerators. Design and evaluate RL environments, run experiments, and deliver results into training runs, collaborating with researchers, engineers, and performance specialists to push scalable RL infrastructure and safe, beneficial AI. Strong emphasis on accelerators, ML frameworks, and end-to-end integration across kernels and model code.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Anthropic
Anthropic
4 months ago

Research Engineer, Performance RL (Reinforcement Learning)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 6 hours agoStatus: Live

Job Summary

Join the Code RL team as a Research Engineer, advancing models’ ability to safely write correct, fast code for accelerators. Design and evaluate RL environments, run experiments, and deliver results into training runs, collaborating with researchers, engineers, and performance specialists to push scalable RL infrastructure and safe, beneficial AI. Strong emphasis on accelerators, ML frameworks, and end-to-end integration across kernels and model code.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Research & Scientific (R&D)

Key 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.

Key Requirements

  • •Expertise with accelerators (CUDA, ROCm, Triton, Pallas) and 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 building beneficial systems
  • •Bachelor's degree in a related field or equivalent experience
Experience:Reinforcement learningAI
Education:Bachelor's
Skills:CommunicationProblem-solvingTeamwork
Languages:English
Tech Stack:CUDAROCmTritonPallasJAXPyTorchDistributed systemsKernels

Eligibility

Work Authorization:Sponsorship available.

Company Brief

Anthropic
Develops large-scale AI systems and safety research to create reliable, steerable, and interpretable AI assistants and models for commercial and research applications.
Industry: AI & Machine Learning
Company Size: Enterprise (1,001+ employees)
Growth: Scaleup
Valuation: Unicorn (USD 1B+)
Funding: Series C
Headquarters: San Francisco, United States
Founded: 2021
WebsiteLinkedIn