Research Engineer – Knowledge Team

About the role

We are looking for Research Engineers to redesign how Claude interacts with external data sources. You will create new architectures for organizing information and train language models to use them effectively.

Key responsibilities

• Design and implement new information‑architecture strategies from scratch.
• Fine‑tune and apply reinforcement learning to teach language models to interact with these architectures.
• Build rigorous knowledge‑base evaluation sets to surface failure modes.
• Design and evaluate advanced agentic search capabilities.

Required profile

• Very experienced Python programmer who writes reliable, high‑quality code.
• Strong machine‑learning research background.
• Experience developing software that utilizes Large Language Models such as Claude.
• Results‑oriented with a bias toward flexibility and impact.
• Willingness to pick up tasks beyond the core description and enjoy pair programming.
• Interest in partnering with world‑class ML researchers and caring about societal impacts.

Required skills

• Python programming
• Machine‑learning research
• Large Language Model development (Claude)
• Reinforcement learning
• Agentic system development
• Scalable distributed information‑retrieval systems
• Search engines, knowledge graphs, RAG, indexing, ranking, query understanding, distributed data processing

What we offer

• Annual salary $350,000–$850,000 USD
• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Office space in San Francisco for collaboration