Senior Software Engineer, RL Post-Training Frameworks
$184k - $357k • US, CA, Santa Clara
Posted 1mo ago
Job Location
US, CA, Santa Clara
Tech Stack
Remote Work Policy
On-site
Categories
AI Research Engineer
About the job
NVIDIA is building an RL Frameworks engineering team to develop open-source tools and infrastructure for AI researchers and post-training teams. This role focuses on the challenging infrastructure required for reinforcement learning, which enables models to reason, follow complex instructions, and act as autonomous agents. The work involves coordinating inference, rollout generation, and training across heterogeneous hardware at scale, pushing the limits of distributed systems. The team spans the full software stack, from collaborating with researchers to contributing to RL frameworks and improving distributed runtimes.
Responsibilities
- Architect and build scalable RL post-training infrastructure from single GPU experimentation to production across thousands of nodes.
- Optimize RL training-inference-rollout loops on GPUs, CPUs, and LPUs for performance.
- Contribute to and improve the performance and usability of open-source RL frameworks.
- Partner with teams owning RL frameworks and CPU-driven rollout workloads (tool-use, code execution, agentic environments).
- Ensure fault tolerance, elastic scaling, and fast restarts for long-running distributed training jobs.
- Advocate for researcher and partner needs with NVIDIA's networking, math library, and compiler teams.
- Work with hardware teams to leverage next-generation hardware capabilities in post-training workloads.
Requirements
- MS or PhD in Computer Science, Computer Engineering, or related field (or equivalent experience).
- 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 in production at a frontier AI lab, hyperscaler, or major technology company.
- Strong verbal and written communication skills and ability to collaborate across organizational and geographic boundaries.
- Depth in Reinforcement learning for LLM post-training (RLHF, PPO, GRPO, DPO, reward modeling), including distributed execution challenges.
- Depth in PyTorch internals, including distributed training primitives (FSDP, tensor parallelism, pipeline parallelism).
- Depth in Kubernetes runtime internals (container lifecycle, pod scheduling, resource quotas, GPU allocation).
- Depth in end-to-end distributed systems design (service boundaries, data flows, consistency models, failure modes, recovery approaches).
Benefits
- Highly competitive salaries
- Comprehensive benefits package
- Equity
- Eligibility for benefits and equity