Reinforcement Learning Post-Training Engineer

Reinforcement learning post-training is driving some of the most significant capability gains in AI today. It is the process that teaches a model to reason through hard problems, follow complex instructions, and act as an autonomous agent.

It is also one of the hardest infrastructure challenges in the field.

RL requires inference, rollout generation, and training running in a continuous loop. The rollout step is what makes it hard: the model must interact with environments, tools, and other models to produce the signal that drives learning.

Coordinating actor, critic, and reward models across heterogeneous hardware at scale pushes the limits of what distributed systems can do.

NVIDIA is building an RL Frameworks engineering team to develop the open-source tools and infrastructure that AI researchers and post-training teams depend on.

The team spans the full software stack, from collaborating closely with the researchers and labs pushing the frontier, to contributing to RL frameworks like VeRL, Miles, and TorchTitan, to improving the distributed runtimes they depend on, including Ray and Monarch.

• Whether your strength is working with researchers to understand and address their needs
• Optimising deep learning frameworks at this scale, or building distributed infrastructure, we want to hear from you. Come join us to build the systems that enable the next generation of AI.

What you will be doing

• You will architect and build RL post-training infrastructure that scales efficiently from experimentation on a single GPU to production across thousands of nodes.
• This means:
  • Tuning RL training-inference-rollout loops on GPUs, CPUs, and LPUs for performance where it matters.
  • Contributing to and improving the performance and usability of open-source RL frameworks.
  • Partnering with the teams who own them.
• The role also spans:
  • Fault tolerance
  • Elastic scaling
  • Fast restarts so long-running distributed training jobs survive failures, stragglers, and resource contention.
• Beyond GPU-accelerated training, this work includes:
  • Partnering with teams building CPU-driven rollout workloads, including:
    • Tool-use
    • Code execution
    • Agentic environments
  • Supplying the systems and framework engineering needed to run them efficiently alongside GPU- or LPU-accelerated generation and GPU-accelerated training.
• It also means:
  • Championing researcher and partner needs with NVIDIA’s networking, math library, and compiler teams so the capabilities RL workloads require get prioritised and delivered.
  • Working with hardware teams to take advantage of next-generation hardware capabilities in post-training workloads.