Senior Multi-Agent RL Research Scientist

Alex Loftus; New York (NY); Hybrid; USD 500,000 - 850,000; Full time

Job summary

Anthropic is seeking researchers to advance training of multi-agent systems and to scale reinforcement learning for language models, with a focus on safety, interpretability, and steerability. The role includes building training environments and benchmarks to maximize Claude’s performance and reliability.

You will work with researchers and product teams to solve core challenges in deploying agents at scale, contributing to mission-driven, high-impact projects in a fast-paced environment.

Qualifications

• Minimum education defined as Bachelor's degree or equivalent.
• Experience with large-scale RL on language models is preferred.
• Experience training multi-agent systems is desirable.
• Strong communication and collaboration with researchers.

Responsibilities

• Help create and optimize environments and data for model training that maximize Claude’s performance.
• Ideate, develop, and compare agent harness configurations for memory, context, and communication.
• Design and implement rigorous benchmarks for large-scale agentic tasks.
• Collaborate with product org to apply agents to company products.

Skills

Large-scale RL

Multi-agent systems

Research collaboration

Education

Bachelor’s degree or equivalent

Job description

Anthropic is seeking researchers to advance training of multi-agent systems and to scale reinforcement learning for language models, with a focus on safety, interpretability, and steerability. The role includes building training environments and benchmarks to maximize Claude’s performance and reliability.

You will work with researchers and product teams to solve core challenges in deploying agents at scale, contributing to mission-driven, high-impact projects in a fast-paced environment.