Senior Manager, Software Engineering - RL Post-Training Frameworks
Core
Lead strategy and team building for NVIDIA's reinforcement learning post-training frameworks and infrastructure to enable AI systems to reason, use tools, and act as agents at scale.
Role type
Senior Manager, Software Engineering (RL Frameworks)
Builds
Open-source RL frameworks (VeRL, Miles, Slime, SkyRL, TorchTitan) and underlying systems (Megatron-Core, Ray, Kubernetes, NIXL, SGLang) for researchers and model builders.
Domain
Artificial Intelligence / Distributed Systems / High-Performance Computing
Deliverable
production ML models
Required skills
Distributed systems architecture, AI framework development, team leadership, technical strategy, open-source collaboration, performance benchmarking, cross-organizational influence
Preferred skills
RL post-training algorithms (RLHF, PPO, GRPO, DPO), runtime/orchestration systems (Ray, Kubernetes, Slurm), GPU scaling (thousands of GPUs), NVIDIA platform components (CUDA, NCCL, TensorRT-LLM)
Responsibilities
Define RL framework strategy and investment priorities, build and develop engineering teams, drive cross-organizational execution, establish engineering workflows and metrics, coach engineers on open-source contributions, partner with research and product teams
Seniority
Senior, hands-on IC leadership
