Epsilon Health
Research Engineer - Data Quality & Evals
- Confirmed live in the last 24 hours
- No salary listed
- Mid level
- Full-time
- On-site · San Francisco, CA
- 2+ yrs exp
- Added 1 month ago
About this role
This Research Engineer role focuses on ensuring data quality and evaluating model performance within a healthcare AI company specializing in medical imaging. You'll build and maintain data filtering pipelines, design robust evaluation methodologies for report generation, and proactively identify and address bottlenecks within the ML research team. This position offers a unique opportunity to directly impact patient outcomes through cutting-edge AI.
What you'll do
- Develop data filtering and curation pipelines for clean training sets.
- Design model-based data quality signals for human review.
- Collaborate with radiologists to define quality criteria and create scalable filters.
- Develop evaluation methodologies for report generation beyond text overlap.
- Build and maintain clinical benchmark sets.
- Develop and validate model-based evaluators against radiologist judgment.
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Epsilon Health
- Industry
- Technology & Software
Likely interview questions
- Describe your experience with data quality techniques like deduplication or label noise detection.
- How have you designed evaluation metrics for generative models in the past?