AI Research Engineer – Reinforcement Learning

About the role

We are seeking an AI Research Engineer specialized in Reinforcement Learning to join a globally distributed team based in Luxembourg. The role combines cutting‑edge research with hands‑on implementation of RL algorithms for real‑world applications in a remote‑first environment.

Key responsibilities

• Design, develop and deploy advanced reinforcement learning algorithms for simulated and real‑world environments.
• Build, run and monitor large‑scale RL experiments, tracking performance metrics and benchmark results.
• Create high‑quality simulation environments and training datasets tailored to domain‑specific challenges.
• Optimize RL pipelines by addressing exploration strategies, policy divergence, reward instability and computational efficiency.
• Collaborate with engineering and research teams to integrate RL agents into production systems.
• Define success metrics and continuously monitor deployed RL models for robustness and scalability.
• Document experimental findings and contribute to ongoing AI research initiatives.

Required profile

• Degree in Computer Science, AI, Machine Learning or related field; PhD preferred.
• Strong research background in reinforcement learning, machine learning or NLP with proven contributions to advanced AI projects.
• Hands‑on experience with large‑scale RL experiments, including online methods such as Group Relative Policy Optimization (GRPO).

Required skills

• Reinforcement learning
• Machine learning
• Natural language processing (NLP)
• Group Relative Policy Optimization (GRPO)

What we offer

• Opportunity to work on frontier AI research in a remote‑first, innovative environment.
• Collaboration with a diverse, globally distributed research team.