Research Scientist, LLM Post-Training

Lila Sciences is seeking a Research Scientist specializing in Large Language Model (LLM) post-training to join our team in either San Francisco, CA, or Cambridge, MA. As a Machine Learning Research Scientist I/II in LLM Inference, you will lead research on training and serving large language models for scientific applications.

In this role, you will develop and optimize LLM post-training strategies, including Supervised Fine-Tuning (SFT), Reinforcement Learning with Human Feedback (RLHF), and Reinforcement Learning with verifiers. You will design test-time compute and efficient inference mechanisms for complex tool use environments, build scalable evaluations for LLM performance on scientific reasoning, and explore the limits of frontier LLM-based approaches for scientific tasks, quantifying their failure modes.

The ideal candidate will have a strong background in LLM training and deployment, research experience in scalable compute techniques, and a track record of publications or contributions to open-source frameworks. Experience applying LLMs to scientific or technical data and working in collaborative cross-functional machine learning environments is a plus.

We offer competitive compensation, including bonus potential and generous early equity. The expected base salary range for this position is $176,000 to $304,000 USD. The final offer will reflect your unique background, expertise, and impact.

Lila Sciences is the world’s first scientific superintelligence platform and autonomous lab for life, chemistry, and materials science. We are pioneering a new age of boundless discovery by building the capabilities to apply AI to every aspect of the scientific method. We are introducing scientific superintelligence to solve humankind's greatest challenges, enabling scientists to bring forth solutions in human health, climate, and sustainability at a pace and scale never experienced before.