Research Scientist — Reinforcement Learning (Foundation Models)

Join our team as a Research Scientist specializing in Reinforcement Learning. In this role, you will focus on integrating RL into the adaptation and improvement of foundation models for industrial use. You will work on human-in-the-loop reinforcement learning, develop RL methods for industrial foundation models, and transition research to deployment. Candidates should have a PhD or equivalent experience in reinforcement learning/machine learning, strong programming skills, and a passion for real-world applications of RL.

Missions

• Research and develop reinforcement learning methods that integrate with foundation models used in production.
• Design feedback interfaces and signals that are practical in real operational settings, turning expert validation into a reliable learning signal.
• Build evaluation protocols aligned with real constraints, and work closely with scientists and engineers to ship demonstrators that connect benchmarks to field outcomes.

Profil recherché

* PhD (preferred) or equivalent research experience in **Reinforcement Learning / Machine Learning**.

* Strong foundations in RL (e.g., policy optimization, off-policy learning, offline RL, exploration, credit assignment).

* Ability to design rigorous experiments, debug failure modes, and iterate fast with scientific discipline.

* Strong programming skills (Python; deep learning stack such as PyTorch).

**Nice to have**

* Experience with real-world RL constraints (noisy/limited feedback, safety requirements, deployment considerations).

* Comfort with complex data modalities (time series, scientific/industrial signals, multimodal setups).

* Publications or open research artifacts in RL / sequential decision-making.

**Why join**

* Work on RL problems that matter in the real world: **expert feedback loops, uncertainty reduction, and mission-critical constraints**.

* A research culture that values clarity, rigor, and humility and that connects fundamental ideas to deployable systems.

* High ownership in a small team: you’ll shape direction, not just execute tasks.