About the role: We are looking for Research Engineers to help us redesign how Claude interacts with external data sources. Many of the paradigms for how data and knowledge bases are organized assume human consumers and constraints. This is no longer true in a world of LLMs! Your job will be to design new architectures for how information is organized, and train language models to optimally use those architectures.Responsibilities:

Designing and implementing from scratch new information architecture strategiesPerforming finetuning and reinforcement learning to teach language models how to interact with new information architecturesBuilding “hard” knowledge base eval sets to help identify failure modes of how language models work with external dataDesigning and evaluating advanced agentic search capabilities.You may be a good fit if you:

Are a very experienced Python programmer who can quickly produce reliable, high quality code that your teammates love usingHave good machine learning research experienceHave experience developing software that utilizes Large Language Models such as ClaudeAre results-oriented, with a bias towards flexibility and impactPick up slack, even if it goes outside your job descriptionEnjoy pair programming (we love to pair!)Want to partner with world-class ML researchers to develop new LLM capabilitiesCare about the societal impacts of your workHave clear written and verbal communicationStrong candidates will also have experience with:

Collaborating with product teams to quickly prototype and deliver innovative solutionsBuilding complex agentic systems that utilize LLMsDeveloping scalable distributed information retrieval systems, such as search engines, knowledge graphs, RAG, indexing, ranking, query understanding, and distributed data processing

#J-18808-Ljbffr