ML Systems Engineer - Model Training and Infrastructure (SWE-focused LLMs)

Sourced from jobs.ashbyhq.com

Cosine is seeking an ML Systems Engineer to train their Lumen models, open-source-based software engineering LLMs. The role involves developing reinforcement learning training environments, building large-scale synthetic data pipelines, and constructing the ML platform for distributed training. You will work across the full model-training stack, from supervised fine-tuning to reward function design, in a high-ownership, in-office environment in London.

• Participate in end-to-end training of models: supervised fine-tuning on curated code and conversation datasets, and RL to align models with software-engineering objectives.
• Develop and manage synthetic data generation pipelines to curate datasets for future training runs.
• Design, build and deploy containerized services using Docker and Kubernetes to enable RL infrastructure.
• Build and maintain the training platform for model architecture experiments, training, and evaluations at scale.
• Ideate on novel and opinionated reward functions for training SWE agents.
• Collaborate closely with infra, product, and research to decide what to train next, how to train it, and how to measure improvement.

• Strong software engineering or computer science background, typically 3-5 years of experience.