Description
Anthropic is looking for a Staff+ Research Scientist to work on Multi-Agent systems. The successful candidate will help create and optimise environments and data for model training to maximise Claude's performance on agentic tasks.
Responsibilities:
- Help create and optimise environments and data for model training that maximise Claude's performance or ease of use on agentic tasks
- Ideate, develop, and compare the performance of different agent harness configurations
- Design and implement rigorous quantitative benchmarks for large-scale agentic tasks
- Work with the product organisation to find solutions to challenges in applying agents to products
Requirements:
- Experience with large-scale reinforcement learning on language models
- Experience training multi-agent systems
- Strong communication skills and ability to work with researchers
- Passion for making powerful technology safe and societally beneficial
The annual compensation range for this role is $500,000 - $850,000 USD.
Anthropic offers competitive compensation and benefits, including optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space.
This listing is enriched and indexed by YubHub. To apply, use the employer's original posting:
https://job-boards.greenhouse.io/anthropic/jobs/4017544008