Research Engineer / Research Scientist, Data Quality & Evaluations
Epsilon Health, San Francisco, CA
The role
We're looking for an exceptional Research Engineer or Research Scientist to advance how we curate data and evaluate frontier AI models for medical imaging.
You'll own the systems and methodologies that determine the quality of our training data and how we measure model performance, building the foundation for reliable, clinically accurate AI.
You'll tackle fundamental challenges in data-centric machine learning, multimodal evaluation, and clinical reliability, from identifying subtle dataset errors to developing rigorous benchmarks for radiology report generation.
Unlike traditional research labs, you'll work with continuously growing real-world clinical data and feedback from practicing radiologists, developing evaluation methods that connect offline research performance with real-world clinical outcomes.
You'll work across our research team, collaborating closely with scientists and engineers developing vision foundation models, VLMs, and post-training methods. This is a highly autonomous role with the opportunity to identify critical research bottlenecks and solve them end to end.