Research Engineer, Agents

Job Description

Anthropic is seeking a Research Engineer to join their team and focus on advancing agentic systems powered by Claude. This role involves maximizing Claude's performance on agentic tasks, developing tools for agents, and discovering prompt engineering best practices. The Research Engineer will also contribute to automated evaluation of Claude models and prompts, collaborate with the product organization, and help optimize data mixes for model training.Responsibilities:

• Finetune new capabilities into Claude.
• Ideate, develop, and compare the performance of different tools for agents.
• Systematically discover and test prompt engineering best practices for agents.
• Develop automated techniques for designing and evaluating agentic systems.
• Assist with automated evaluation of Claude models and prompts.
• Work with our product org to find solutions to our most vexing challenges applying agents to our products.
• Help create and optimize data mixes for model training.
• Help to create and maintain the infrastructure required for efficient prompt iteration and testing.

Requirements:

• 7+ years of ML and software engineering experience.
• High-level familiarity with the architecture and operation of large language models.
• Extensive prior experience exploring and testing language model behavior.
• Experience prompting and/or building products with language models.
• Good communication skills.
• Passion for making powerful technology safe and societally beneficial.
• Interest in emerging research and industry trends.
• Bachelor's degree in a related field or equivalent experience.

The role offers:

• Competitive compensation and benefits.
• Optional equity donation matching.
• Generous vacation and parental leave.
• Flexible working hours.