Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Claude Code, Codex, Gemini, Cursor and Grok
Connect

Anthropic

Staff Research Engineer Multi Agent Scaling

Posted Updated

Description

You will design, run, and interpret large-scale agent-team experiments. You will build and scale reliable execution systems, develop evaluations and metrics, investigate bottlenecks, debug failures at scale, and enable other research teams to use the platform.

Responsibilities

  • Design, run, and interpret large-scale experiments on agent teams
  • Investigate performance and efficiency as team size, compute, and task horizon grow
  • Build and scale reliable systems for large agent teams
  • Design trustworthy evaluations for long-horizon problems
  • Build tooling and metrics for understanding agent-team behavior
  • Enable research teams to run experiments on the platform and communicate findings clearly

Requirements

  • Significant software engineering, machine learning, or research engineering experience
  • Experience owning a substantial system, evaluation, benchmark, agent product, or research project end to end
  • Quantitative reasoning about complex systems
  • Ability to work from vague questions
  • Clear written and verbal communication
  • Bachelor’s degree or equivalent education, training, or experience

Benefits

  • Visa sponsorship efforts
  • Optional equity donation matching
  • Generous vacation
  • Parental leave
  • Flexible working hours

Skills

Apply

See also