We are looking for Research Engineers to help us redesign how Language Models interact 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 Language Models! 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 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

Extending traditional ideas like RAG into heterogeneous data types (image, tables, relational data, etc.)

Have significant Python programming experience

Have good machine learning research experience

Have experience developing software that utilizes Large Language Models such as Claude

Are results-oriented, with a bias towards flexibility and impact

Pick up slack, even if it goes outside your job description

Enjoy pair programming (we love to pair!)

Want to partner with world-class ML researchers to develop new LLM capabilities

Care about the societal impacts of your work

Have clear written and verbal communication

Strong candidates will also have experience with:

Developing scalable distributed information retrieval systems, such as search engines, knowledge graphs, indexing, ranking, query understanding, and distributed data processing

Conducting research to advance search quality and knowledge base systems

Understanding Retrieval Augmented Generation (RAG) and its limitations

Collaborating with product teams to quickly prototype and deliver innovative solutions