LLM Data Researcher
At a glance
Mid-level AI Research role at Clera. Barcelona · full-time.
Pay not stated AI Research salary
aimlroles summary, based on the employer's posting.
What you'll do
- Post-train models on expert-created datasets, then measure changes and investigate when results fail to improve
- Build evaluations of frontier language models in law, medicine, finance or other stated domains
- Choose and use approaches such as supervised fine-tuning, reinforcement learning and preference-based training
- Use experimental results to shape dataset requirements and product plans
- Publish findings in research papers, public benchmarks and blog posts
What you bring
- A completed or nearly finished machine learning or NLP PhD, or an equivalent record of research work
- Practical experience training and assessing language models end to end, including reinforcement learning or preference optimization
- A track record creating robust LLM evaluations or benchmarks, with applied research in model post-training
- Professional English and the ability to explain technical results to research, operations and client audiences
Who this fits
This hands-on research role suits an early-career researcher, from near PhD completion through a few years of postdoctoral work. You’ll work on-site in Barcelona, Spain; relocation support is available.
From the employer
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 familiarity with AI tools and coding agents.
Publications at leading machine learning or NLP venues, or experience building evaluation tools, are a plus.
Professional English proficiency.
Compensation & Benefits
Competitive salary, equity, and relocation support are available. Salary range and visa sponsorship policy were not specified.
Location
On-site in Barcelona, Spain. Relocation support is available.