USD per year
About Periodic Labs: Periodic Labs is an AI + physical sciences lab focused on building state-of-the-art models to enable novel scientific discoveries. The organization is well funded, rapidly growing, and values team members who take ownership and solve problems without boundaries or bureaucracy. The team embraces learning new tools and science to advance their mission. The role of Research Engineer - Posttraining involves post-training frontier models to autonomously manage various parts of the scientific discovery pipeline. Responsibilities include generating hypotheses, designing experiments conducted in a real lab, operating advanced scientific equipment, creating high-quality evaluation and training tasks, scaling reinforcement learning (RL) environments, designing reward functions, and running large-scale RL runs. The position requires collaboration with leading physical sciences experts to automate scientific discovery. Ideal candidates have experience in:
- Creating and scaling RL environments for large language models (LLMs)
- Developing high-quality evaluations for frontier models
- Collaborating with domain experts to define evaluation criteria, tools, and agent environments
- Designing training datasets and reward functions with LLMs and/or human trainers
- Training frontier LLMs using reinforcement learning
Periodic Labs aims to create an AI scientist and autonomous laboratories for them to operate, focusing on accelerating science in the physical sciences. They build AI scientists and autonomous labs to generate high-quality experimental data, enabling new scientific discoveries and applications such as discovering higher-temperature superconductors and aiding semiconductor manufacturers.
View Company Profile