Researcher, Training - London

OpenAI's Training team is responsible for producing the large language models that power our research, our products, and ultimately bring us closer to AGI. As a member of the training team, you will push the frontier of LLM development for OpenAI's flagship models, enhancing intelligence, efficiency, and adding new capabilities. This role is based in London and uses a hybrid work model of 3 days in the office per week.

Responsibilities

Design, prototype and scale up new architectures to improve model intelligence; Execute and analyze experiments autonomously and collaboratively; Study, debug, and optimize both model performance and computational performance; Contribute to training and inference infrastructure

Requirements

Deep understanding of LLM architectures; sophisticated understanding of model inference; hands-on empirical approach; equally happy coming up with a creative breakthrough, investing in strengthening a baseline, designing an eval, debugging a thorny regression, or tracking down a bottleneck; experience landing contributions to major LLM training runs; ability to thoroughly evaluate and improve deep learning architectures in a self-directed fashion; motivation to safely deploy LLMs in the real world; knowledge of state of the art transformer modifications for efficiency

Nice to have

Architecture design; long-context and efficient attention; optimization; science of scaling

Benefits

Relocation support; hybrid schedule with option to work from home on Thursdays and Fridays; offices set up for focus and connection with adjustable desks, phone booths, conference rooms, stocked kitchens, and cozy spots to unwind or catch up with teammates