Staff Research Engineer, Multi-Agent Scaling

📋 Description

• Design, run and interpret large-scale experiments on agent teams, reasoning rigorously about what
• Investigate how performance and efficiency change as team size, compute and task horizon grow, and
• Build and scale the systems that run very large agent teams reliably, and debug the failures that
• Design evaluations for long-horizon problems, and keep their results trustworthy
• Build the tooling and metrics that let researchers see what a large agent team is doing and why
• Partner with research teams across Anthropic so they can run their own experiments on the platform

🎯 Requirements

• Have significant software engineering, ML or research engineering experience
• Have owned something substantial end to end, such as a large system, an evaluation or benchmark, an
• Genuinely enjoy both research and engineering work
• Think quantitatively about complex systems, and think twice before trusting a number
• Can work from a vague question rather than a spec
• Are results-oriented, with a bias towards flexibility and impact

🎁 Benefits

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Office space in which to collaborate with colleagues