Director, Reinforcement Learning & Agentic Post-Training
Core
Lead the technical strategy and execution for training LLM-based agents to operate autonomous supply chain software using reinforcement learning and post-training techniques.
Role type
Director, Reinforcement Learning & Agentic Post-Training
Builds
Production LLM agents that reason over supply chain state, use tools, interact with enterprise workflows, and execute multi-step operational tasks.
Domain
Supply Chain / Autonomous Agents / Reinforcement Learning
Deliverable
production ML models
Required skills
Reinforcement Learning (PPO, GRPO, offline RL), LLM post-training (SFT, DPO, RLHF/RLAIF), Tool-use environment design, Reward modeling & verifiers, Evaluation frameworks for agent behavior, Python, PyTorch, Distributed training systems, Production engineering tradeoffs
Preferred skills
Simulated enterprise software environments, NVIDIA stack (Nemotron, NeMo, Megatron, vLLM, Ray), Supply chain domain expertise (planning, warehouse, transportation), Agent safety systems design
Technologies
Python, PyTorch, NVIDIA NeMo, Megatron, vLLM, Ray, PPO, GRPO, DPO, RLHF, SFT
Responsibilities
Lead technical strategy for RL and post-training; Build and manage ML engineering teams; Design training environments for agent tool use; Develop reward models and evaluation harnesses; Partner with domain experts to create trainable workflows; Guide model improvement across optimization techniques; Establish engineering standards for reproducibility and production monitoring.
Seniority
Director, hands-on technical leadership
