RL & LLMs Engineer for Autonomous Supply Chain

JDA Software; Paris; Sur place; EUR 70 000 - 110 000; Plein temps

Résumé du poste

Blue Yonder is seeking an ambitious ML Engineer in Paris to help build training, evaluation, and tooling systems for AI-powered decision-making in supply chain. The role centers on LLMs, agent environments, and reinforcement learning, with emphasis on robust evaluation and data pipelines.

You will design experiments, ship production code, and shape how LLMs are used inside agent-based systems. A strong background in RL training with LLMs, reward modeling, and Python/PyTorch is required, with a

Qualifications

• You've trained or fine-tuned LLMs.
• Experience with AI agents and RL environments in production.
• Proficiency in Python and PyTorch.
• Hands-on experience with RL techniques (reward shaping, policy optimization).
• Ability to balance research exploration with shipping working code.

Responsabilités

• Design and implement LLM-powered agent environments for supply chain decision-making.
• Fine-tune and evaluate LLMs for domain-specific reasoning and decision support.
• Design, test, and iterate on reward functions that capture the behaviors we want from LLM agents.
• Review LLM traces and rollouts to understand model reasoning, failure modes, reward hacking, and shortcut behaviour.
• Identify when an LLM is exploiting the reward function or optimizing for proxy metrics.
• Improve reward models, environment design, prompts, tools, and feedback loops.
• Build evaluation frameworks to measure model quality, agent performance, robustness, and failure modes.
• Create data pipelines for training, fine-tuning, preference data, synthetic data generation, and human feedback collection.
• Develop tooling that improves how the team builds, tests, debugs, and deploys AI-assisted workflows.
• Experiment with RL, RLHF, RLAIF, reward shaping, policy optimization, and agent training techniques.
• Document what works, what fails, and why, so we can compound our learnings over time.
• Stay close to the frontier of LLMs, agents, evaluations, and applied AI engineering.

Connaissances

LLM fine-tuning

Python

PyTorch

Reinforcement learning

RL techniques

Reward modeling

Agent environments

Description du poste

Blue Yonder is seeking an ambitious ML Engineer in Paris to help build training, evaluation, and tooling systems for AI-powered decision-making in supply chain. The role centers on LLMs, agent environments, and reinforcement learning, with emphasis on robust evaluation and data pipelines.

You will design experiments, ship production code, and shape how LLMs are used inside agent-based systems. A strong background in RL training with LLMs, reward modeling, and Python/PyTorch is required, with a