Senior Multi-Agent RL Research Scientist

Anthropic Limited; New York (NY); On-site; USD 500,000 - 850,000; Full time

Job summary

Anthropic Limited in New York, USA, seeks researchers to advance multi-agent reinforcement learning at scale, specializing in training Claude within large groups. You will design environments and agent harness configurations to optimize performance and safety.

Collaborating with product teams, you will develop rigorous benchmarks for agentic tasks and contribute to deploying powerful AI responsibly.

Qualifications

• Experience with large-scale RL on language models.
• Experience training multi-agent systems.
• Strong foundation and problem-solving approach.
• Strong communication skills.
• Passion for making powerful technology safe and societally beneficial.
• Mission-driven with fast-paced, impactful work.

Responsibilities

• Help create and optimize environments and data for model training that maximize Claude’s performance or ease of use on agentic tasks
• Ideate, develop, and compare the performance of different agent harness configurations (eg memory, context management, communication architectures for agents)
• Design and implement rigorous quantitative benchmarks for large scale agentic tasks
• Work with our product org to find solutions to our most vexing challenges in applying agents to our products

Skills

Large-scale RL

Multi-agent training

Communication skills

Foundations & problem-solving

Education

Bachelor’s degree

Job description

Anthropic Limited in New York, USA, seeks researchers to advance multi-agent reinforcement learning at scale, specializing in training Claude within large groups. You will design environments and agent harness configurations to optimize performance and safety.

Collaborating with product teams, you will develop rigorous benchmarks for agentic tasks and contribute to deploying powerful AI responsibly.