Specialty
The role
Cohere, an enterprise AI company, is hiring a Research Engineer for its Integration/RL team, which builds the algorithms and infrastructure for LLM post-training with large-scale distributed reinforcement learning. Applicants may work anywhere between UTC-06:00 and UTC+01:00.
What you will do
- Design and write scalable software for training models.
- Develop tools that support and speed up research and LLM training.
- Coordinate with infrastructure, efficiency, serving and science teams on the post-training ecosystem.
- Implement techniques to speed up training cycles across SFT, offline preference and RL.
- Experiment with ideas on the cluster and data infrastructure.
What they ask for
- Extremely strong software engineering skills, with a preference for test-driven development and clean code.
- Proficiency in Python and ML frameworks such as JAX, PyTorch or XLA/MLIR.
- Experience using and debugging large-scale distributed training, including memory and speed profiling.
- Working hours between UTC-06:00 and UTC+01:00.
- Bonus: Kubernetes and Ray, post-training experience, ML or RL research background.
What they offer
- Weekly lunch stipend
- Health and dental benefits with a mental health budget
- RRSP matching, 401(k) or pension
- Parental leave top-up for up to 6 months
- 6 weeks paid vacation
- $500 home office stipend and co-working benefit
This is our own short reading of the posting. The full description, and anything that has changed since, is on Cohere's careers page behind the apply button.
