Clera

LLM Data Researcher

Barcelona

Python · TensorFlow · PyTorch

ABOUT THE ROLE

Join the founding research team at an AI data company to investigate whether expert-authored datasets improve frontier language models and help guide future product development. This hands-on role focuses primarily on rigorous experimentation, with collaboration across clients, partners, and the data team.

WHAT YOU'LL DO

  • Post-train models on expert-authored datasets, measure performance changes, and diagnose cases where the data does not improve results.
  • Design and run evaluations of frontier language models in domains such as law, medicine, and finance.
  • Select and apply suitable methods, including supervised fine-tuning, reinforcement learning, and preference-based training.
  • Turn research findings into dataset specifications and product direction.
  • Share results through research papers, public benchmarks, and blog posts.

WHAT WE'RE LOOKING FOR

  • A completed or near-completed PhD in machine learning or NLP, or an equivalent research record demonstrated through publications or AI research work.
  • Hands-on experience post-training and evaluating language models end to end, including methods such as SFT, RLHF, RLVR, reward modeling, and preference optimization.
  • Experience designing or building robust LLM evaluations and benchmarks, with practical research on LLM reinforcement learning or post-training.
  • An early-career research profile, from near-completion of a PhD to a few years of postdoctoral experience.
  • Ability to explain technical findings to researchers, operations teams, and non-technical clients.
  • Daily familiar
Read the rest on jobs.ashbyhq.com