Staff Machine Learning Research Engineer, Agent Post-training - Enterprise GenAI: Scale

Scale's mission is to accelerate the development of AI applications and has been a leading AI data foundry for 9 years.

This role is with the Enterprise ML Research Lab. As a Staff Agent Post-Training Machine Learning Research Engineer (MLRE), you will be responsible for building Scale's next-generation Agent RL (Reinforcement Learning) training platform. You will build the system that trains best-in-class Agents to achieve state-of-the-art results on real-world enterprise use cases, integrating cutting-edge research into the training stack.

Responsibilities
Train state-of-the-art models (developed internally and from the community) to deploy to enterprise customers.

Research cutting-edge algorithms to integrate directly into the training stack.

Design solutions that enable complex multi-agent systems to learn from both process and outcome-based rewards.

Requirements
5+ years of LLM training in a production environment.

Experience with post-training methods like RLHF/RLVR and related algorithms like PPO/GRPO.

Publications in top conferences such as NEURIPS, ICLR, or ICML within the last two years.

A PhD or Master's degree in Computer Science or a related field.