Description
Reinforcement learning post-training is driving significant capability gains in AI today. It teaches a model to reason through hard problems, follow complex instructions, and act autonomously. NVIDIA is building an RL Frameworks engineering team to develop open-source tools and infrastructure for AI researchers and post-training teams.
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 involves tuning RL training-inference-rollout loops on GPUs, CPUs, and LPUs for performance, contributing to and improving open-source RL frameworks, and partnering with teams who own them.
The role also spans fault tolerance, elastic scaling, and fast restarts for long-running distributed training jobs. You will work with researchers to understand and address their needs, optimize deep learning frameworks, and build distributed infrastructure.
Responsibilities:
- Architect and build scalable RL post-training infrastructure
- Tune RL training-inference-rollout loops on GPUs, CPUs, and LPUs
- Contribute to and improve open-source RL frameworks
- Partner with teams who own RL frameworks
- Ensure fault tolerance, elastic scaling, and fast restarts for distributed training jobs
Requirements:
- MS or PhD in Computer Science, Computer Engineering, or a related field
- 5+ years of professional experience in distributed systems, high-performance computing, deep learning infrastructure, or ML systems engineering
- Strong proficiency in Python and C/C++
- Demonstrated experience building or contributing to large-scale distributed systems or runtime frameworks
- Strong verbal and written communication skills
Nice to Have:
- Experience with reinforcement learning for LLM post-training
- Knowledge of PyTorch internals and distributed training primitives
- Familiarity with Kubernetes runtime internals
- Experience with end-to-end distributed systems design
Benefits: NVIDIA offers highly competitive salaries and a comprehensive benefits package. Learn more at www.nvidiabenefits.com/