Cohere
Member of Technical Staff, Post-Training
$250K–$535K
London +5 · Hybrid · Staff · Full-time · Posted Jun 13, 2025
- Location
- London
San Francisco
New York
Paris
Toronto
Montreal - Experience
- Hands-on experience with large-scale model training and post-training; no number of years specified.
About the job
Advance model post-training research and techniques, and build and ship high-performing models and training software to production.
What you'll do
- Design and write scalable, high-performance software for model training; research and experiment using compute and data infrastructure.
- Post-train models and improve training cycles across supervised fine-tuning (SFT) and reinforcement learning (RL).
- Coordinate with specialist teams to produce models with strong overall performance.
What they ask for
- Extremely strong software engineering skills.
- Proficiency in Python and ML frameworks such as JAX, Pytorch, and XLA/MLIR.
- Experience with distributed training infrastructure and frameworks, including Kubernetes, Slurm, and Ray.
- Hands-on experience with large-scale distributed training and model post-training, especially performance optimization.
Nice to have
- Papers at top-tier venues, such as NeurIPS, ICML, ICLR, AIStats, MLSys, JMLR, AAAI, Nature, COLING, ACL, or EMNLP.
Pay
CA$250K – CA$535K (base salary)
Tools
Python, JAX, Pytorch, XLA/MLIR, Kubernetes, Slurm, Ray
AI focus
Research and advance model post-training, including SFT and RL, to improve frontier model performance and deploy models to production.
Model-written summary · the original posting is authoritative