About this role
Join Clera's founding research team to investigate the impact of expert-authored datasets on frontier language models. You will conduct rigorous experiments, evaluate model performance across diverse domains like law and medicine, and translate research findings into product direction. This role offers a unique opportunity to shape the future of AI data and contribute to cutting-edge research.
What we are looking for 6
- Post-train and evaluate frontier language models using methods like SFT and RLHF
- Design and run evaluations in specialized domains such as law, medicine, and finance
- Translate research findings into dataset specifications and product strategy
- Publish research in leading venues and contribute to public benchmarks
- PhD in ML/NLP or equivalent research record
- Hands-on experience with LLM post-training and evaluation