Research Engineer / Research Scientist, Data Quality & Evaluations

The role

You will develop scalable data filtering, curation, and quality pipelines for medical imaging. You will also design evaluation frameworks for radiology report generation and build research infrastructure.

What you will do

• Develop scalable data filtering, curation, and quality pipelines.
• Explore approaches to detecting label noise, image-report misalignment, and duplicates.
• Design evaluation frameworks for radiology report generation.
• Work with radiologists to translate clinical judgment into evaluation signals.
• Build model-based evaluators, automated grading methods, and human-in-the-loop workflows.
• Develop benchmarks, evaluation pipelines, and continuous regression testing.
• Identify bottlenecks across data, training, and evaluation.
• Contribute to the research community through publications or open-source research.

Required qualifications

• Strong expertise in machine learning, data-centric AI, model evaluation, or research engineering.
• Demonstrated ability to design and build robust data pipelines, evaluation systems, or ML research infrastructure.
• Strong Python programming skills.
• Ability to develop reliable, scalable research tooling.
• Experience in at least one of our core areas: dataset curation and quality, or evaluation of generative and multimodal models.
• Ability to independently identify research bottlenecks, formulate solutions, and execute projects end to end.
• Strong engineering fundamentals and experience working with complex datasets or machine learning systems.
• A rigorous, experimental mindset.

Nice to have

• Experience developing evaluation frameworks for LLMs, VLMs, or other generative models.
• Familiarity with data filtering, deduplication, label-noise detection, or active learning.
• Experience building model-based evaluators, LLM-as-judge systems, or human-in-the-loop annotation workflows.
• Knowledge of clinical evaluation methodologies, including factuality assessment, hallucination detection, or RadGraph-style metrics.
• Background in medical imaging, radiology, clinical NLP, or other healthcare AI applications.
• Experience working with large-scale data processing tools such as Spark, Airflow, or Databricks.
• Publications or open-source contributions in machine learning, data-centric AI, evaluation, or medical AI.

About the company

Epsilon Health is transforming medical imaging and diagnostics by bringing frontier AI into clinical practice. The company is backed by Jack Altman, Uncork Capital, Renegade Partners, and AlleyCorp.