Senior Research Scientist Fmta

DeepL DeepL · AI Frontier · London, United Kingdom · Research

Senior Research Scientist role focused on the post-training stack for large language models, specifically using reinforcement learning to align pre-trained models with tasks and performance goals. The role involves designing, implementing, and deploying research in RL and post-training at scale, with a focus on enabling new capabilities, controllability, and safety. Collaboration with engineering and ML platform teams is key for production deployment.

What you'd actually do

  1. Build and deploy state-of-the-art reinforcement learning pipelines at scale.
  2. Post-train large (multi-modal) models to align them with human intent and enable general capabilities such as reasoning, pushing the boundaries of model performance, safety, and efficiency
  3. Always keep the entire lifecycle of research and production in mind: from idea conception, theoretical modeling, prototyping, ablation studies, all the way to production deployment
  4. Build and foster external collaborations with academic and industrial partners
  5. Follow scientific and technical standards for experimentation, reproducibility, and model evaluation

Skills

Required

  • Python
  • PyTorch
  • TensorFlow
  • JAX
  • mathematics
  • physics
  • computer science

Nice to have

  • working with large compute clusters
  • ML infrastructure
  • deep reinforcement learning (RLHF/RLAIF/RLVR)
  • scaling and deploying LLMs or other foundation models in real-world systems

What the JD emphasized

  • proven track record of driving research in reinforcement learning or large-scale model alignment to production
  • track record of leading self-directed research projects that go well beyond academic exercises and deliver tangible results

Other signals

  • post-training
  • reinforcement learning
  • large language models
  • production deployment