Staff+ Research Scientist (Multi-Agent)

Join Anthropic, a leading AI safety and research company, as a Research Engineer focused on enhancing the capabilities of our language model, Claude. In this role, you will work on various tasks, including fine-tuning Claude for agentic tasks, developing tools for agents, and discovering prompt engineering best practices. You will also assist with automated evaluation of Claude models and prompts, collaborate with the product team, and help create and maintain the infrastructure for efficient prompt iteration and testing.

• Research Engineer (Agent) - Finetune new capabilities into Claude that maximize Claude’s performance or ease of use on agentic tasks.
• Ideate, develop, and compare the performance of different tools for agents (eg memory, context compression, communication architectures for agents).
• Systematically discover and test prompt engineering best practices for agents.

• Have good communication skills and an interest in working with other researchers on difficult tasks
• Have a passion for making powerful technology safe and societally beneficial
• Have spent time prompting and/or building products with language models
• Stay up-to-date and informed by taking an active interest in emerging research and industry trends
• Enjoy pair programming (we love to pair!)
• Have 7+ years of ML and software engineering experience
• Have extensive prior experience exploring and testing language model behavior
• Have at least a high level familiarity with the architecture and operation of large language models
• Developing complex agentic systems using LLMs
• Large-scale RL on language models
• Multi-agent systems
• We require at least a Bachelor's degree in a related field or equivalent experience
• We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed