AI Safety & Alignment Research Scientist

Story Terrace Inc.; Paris; Sur place; EUR 90 000 - 150 000; Plein temps

Résumé du poste

Lexsi Labs in France is seeking a Research Scientist to tackle large‑scale AI alignment, explainability, and safety challenges. The role combines startup culture with rigorous research, offering opportunities to publish and contribute to foundational ML work.

You will advance techniques in ML Observability, collaborate with ML Engineers and SDEs, and influence deployment in cloud or on‑premise environments while pushing the frontiers of safe AI.

Qualifications

• Advanced degree in ML/CS/Math required (MS or PhD).
• Publications or open‑source contributions preferred.
• Experience with DL frameworks and cloud deployment.

Responsabilités

• Work on AI explainability, safety, and alignment problems.
• Choose specialization areas within ML/DL and problem types.
• Develop techniques around ML Observability & Alignment.
• Collaborate with MLEs and SDEs to roll out features and ensure quality.
• Publish papers and present at conferences like arXiv, ICLR, NeurIPS.

Connaissances

ML foundations

Deep learning / RL

Peer‑reviewed publications

TensorFlow / PyTorch

Multi‑modal data handling

Cloud / on‑prem deployment

MLOps fundamentals

Explainability methods

2+ years DL/ML

Transformer / GANs experience

Formation

Master's or PhD in CS or Mathematics

Description du poste

Lexsi Labs in France is seeking a Research Scientist to tackle large‑scale AI alignment, explainability, and safety challenges. The role combines startup culture with rigorous research, offering opportunities to publish and contribute to foundational ML work.

You will advance techniques in ML Observability, collaborate with ML Engineers and SDEs, and influence deployment in cloud or on‑premise environments while pushing the frontiers of safe AI.