Software Engineer, Model Evaluation and Improvement

Job Description

Build datasets and scalable infrastructure to evaluate and improve frontier AI models for scientific applications. Collaborate with scientists and AI labs to translate complex biological tasks into rigorous model evaluation criteria.

Requirements: Requires 2+ years of experience at the intersection of biology and AI, specifically with LLMs for biological applications. Candidates must be comfortable with ambiguity and possess a collaborative mindset for a fast-paced environment.

Key Skills: LLM Evaluation, Dataset Construction, Data Infrastructure, Biology, AI Model Improvement, Scientific Data Analysis, Software Engineering, Prompt Engineering, Pipeline Development, Experimental Design