Research Engineer: Knowledge Architecture for LLMs

Anthropic Limited; San Francisco (CA); Hybrid; USD 350,000 - 850,000; Full time

Benefits offered by this job

Generous vacation and parental leave

Flexible working hours

Office in SF

Job summary

Anthropic Limited in San Francisco is seeking Research Engineers to redesign how Claude interacts with external data sources and to design new information architectures for knowledge integration. You will train language models to work with these architectures, perform finetuning and RL, and build robust evaluation sets.

Collaboration with world-class ML researchers is expected, with a focus on safety, interpretability, and societal impact.

Qualifications

• Very experienced Python programmer with ability to produce reliable, high-quality code.
• Strong machine learning research experience.
• Experience developing software that utilizes Large Language Models such as Claude.
• Results-oriented with a bias towards flexibility and impact.
• Willing to pick up slack beyond job description.
• Enjoys pair programming.
• Wants to partner with world-class ML researchers to develop new LLM capabilities.
• Cares about societal impacts of work.
• Has clear written and verbal communication.

Responsibilities

• Designing and implementing from scratch new information architecture strategies.
• Performing finetuning and reinforcement learning to teach language models how to interact with new information architectures.
• Building “hard” knowledge base eval sets to help identify failure modes of how language models work with external data.
• Designing and evaluating advanced agentic search capabilities.

Skills

Python

ML research

Tools

Claude

Job description

Anthropic Limited in San Francisco is seeking Research Engineers to redesign how Claude interacts with external data sources and to design new information architectures for knowledge integration. You will train language models to work with these architectures, perform finetuning and RL, and build robust evaluation sets.

Collaboration with world-class ML researchers is expected, with a focus on safety, interpretability, and societal impact.