Director, Reinforcement Learning & Agentic Post-Training @ Jda

Director, Reinforcement Learning & Agentic Post-Training at Jda. Location: Paris, Île-de-France, France. Role: leading strategy, managing team, designing environments Requirements: Proven experience leading teams that ship post-trained LLMs with RL/SFT/DPO/RLHF, strong ML engineering background, hands-on experience with reinforcement learning methods, and high proficiency in Python and PyTorch. Category: Research and Development (R&D) Seniority: Senior Level Tools: Python, PyTorch, NVIDIA Nemotron, NVIDIA NeMo, Megatron, vLLM, Ray Commitment: Full Time Workplace: Onsite Languages: pp, English