About the job
Your Contribution at Lila
As a Machine Learning Research Scientist I/II specializing in LLM Inference, you will spearhead research initiatives focused on the training and deployment of large language models for scientific applications.
Your Responsibilities
- Develop and refine post-training strategies for LLMs, including Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Reinforcement Learning with verifiers.
- Design efficient inference mechanisms and compute strategies for complex tool utilization in various environments.
- Create scalable evaluation metrics to assess LLM performance in scientific reasoning tasks.
- Investigate the boundaries of cutting-edge LLM methodologies for scientific challenges and analyze their limitations.

