Distributed training frameworks (megatron, nemo, deepspeed)
Ml ops skills (pipeline automation, job orchestration)
Nvidia Corporation is seeking an experienced engineer to integrate reinforcement learning (RL) capabilities into their agent systems. The role emphasizes operationalizing RL techniques and creating reusable frameworks that empower agent developers
Job Summary
We're hiring an engineer to help us bring reinforcement learning to every agent team at NVIDIA, shaping how autonomous, self-improving agents learn and evolve across the enterprise.
The role sits at the intersection of ML research and production engineering, evaluating emerging approaches, adapting them into enterprise-ready blueprints, and making them available inside sandboxed execution environments.
The work splits between creating enterprise-ready RL capabilities and partnering with agent teams to put them into practice, including building RL cookbooks and environments, and ensuring infrastructure, reliability, and collaboration.
Matching Summary
Match Score: 85
Nvidia Corporation is seeking an experienced engineer to integrate reinforcement learning (RL) capabilities into their agent systems. The role emphasizes operationalizing RL techniques and creating reusable frameworks that empower agent developers.