Member of Technical Staff, Integration/RL Team (Research Engineer)
Cohere · London
1 year ago
RemoteFull_timeLLM post-trainingdistributed reinforcement learningML infrastructure
1 year ago
Workplace
Remote
Employment
Full_time
Location
London
Posted
1 year ago
Summary
Research engineer role focused on building scalable software and infrastructure for LLM post-training, including distributed RL, SFT, and model-training research. The role is remote-friendly and allows applicants to work anywhere between UTC−06:00 and UTC+01:00.
Responsibilities
- Design scalable software for model training
- Develop tools supporting research and LLM training
- Coordinate post-training work across engineering teams
- Implement techniques for faster training cycles
- Experiment with ideas on cluster infrastructure
- Debug complex ML codebases and resolve issues
pythonjaxpytorchxlamlirkubernetesraysftrltest-driven development
LLM post-trainingdistributed reinforcement learningML infrastructurefoundation modelsmodel training
