About this role
Job title: Research Engineer, Knowledge Team
About the Role We are looking for Research Engineers to redesign how Claude interacts with external data sources. You will design new information architectures for organizing data and train language models to optimally use those architectures, enabling more reliable and interpretable AI. This role blends research with practical system-building to push the capabilities of LLMs in data-driven workflows.
What You'll Do
- 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.
What We're Looking For
- Very experienced Python programmer who can quickly produce reliable, high quality code that teammates love using
- Good machine learning research experience
- Experience developing software that utilizes Large Language Models such as Claude
- Results-oriented, with a bias towards flexibility and impact
- Pair programming and willingness to collaborate with world-class ML researchers
- Clear written and verbal communication
Nice to Have
- Collaborating with product teams to quickly prototype and deliver innovative solutions
- Building complex agentic systems that utilize LLMs
- Developing scalable distributed information retrieval systems, such as search engines, knowledge graphs, RAG, indexing, ranking, query understanding, and distributed data processing
Compensation & Benefits
- Annual Salary: $350,000 - $850,000 USD You are trained on data up to October 2023.