Research Engineer, Production Model Post-Training - London

Implement and optimize post-training techniques at scale on frontier language models to improve production safety, alignment, and performance.
Conduct research to develop post-training recipes, including Constitutional AI and RLHF, that directly enhance model quality.
Design, build, and run robust pipelines for fine-tuning and evaluating models across diverse metrics.
Develop tools to measure, monitor, and debug model training and deployment in large-scale distributed systems.
Collaborate with research and engineering teams to translate cutting-edge techniques into production-ready implementations and establish best practices for reliability.
Balance research exploration with engineering rigor, maintain clarity under time pressure, and contribute to safe, responsible AI deployment.