Senior Data Scientist, Medical Imaging

Heartflow•San Francisco, CA

13h•$170,000 - $240,000•Hybrid

About The Position

Heartflow is a medical technology company advancing the diagnosis and management of coronary artery disease, the #1 cause of death worldwide, using cutting-edge technology. The flagship product—an AI-driven, non-invasive cardiac test supported by the ACC/AHA Chest Pain Guidelines called the Heartflow FFRCT Analysis—provides a color-coded, 3D model of a patient’s coronary arteries indicating the impact blockages have on blood flow to the heart. Heartflow is the first AI-driven non-invasive integrated heart care solution across the CCTA pathway that helps clinicians identify stenoses in the coronary arteries (RoadMap™Analysis), assess coronary blood flow (FFRCT Analysis), and characterize and quantify coronary atherosclerosis (Plaque Analysis). Our pipeline of products is growing and so is our team; join us in helping to revolutionize precision heartcare. Heartflow is a publicly traded company (HTFL) that has received international recognition for exceptional strides in healthcare innovation, is supported by medical societies around the world, cleared for use in the US, UK, Europe, Japan and Canada, and has been used for more than 750,000 patients worldwide. We are looking for a Senior Data Scientist with a strong foundation in both statistical data analysis and deep learning to drive our data-centric AI initiatives. In this role, you will be at the forefront of understanding how diverse real-world imaging conditions and technical variables affect image appearance and, in turn, the accuracy and reproducibility of deep learning algorithms. You will own the analytical pipeline to quantify these effects and explore data-driven methods to address them. You will work cross-functionally to translate these insights into downstream algorithm development and product decision-making, including development of annotation protocols to curate high quality annotations for training and validation. If you are drawn to deriving insight from large and messy real-world imaging data, and to communicating and crystalizing solutions from these insights, this is the role for you.

Requirements

Masters or PhD Degree in Data Science, Computer Science, Medical Image Analysis, Statistics, Biomedical Engineering, or a related quantitative field.
5+ years (or 3+ with a PhD) of industry experience in Data Science, Machine Learning, or Image Analysis.
Working command of reproducibility and agreement statistics — variance components, Gage R&R, intraclass correlation, repeatability and reproducibility coefficients, Bland-Altman — and the judgement to separate correctable bias from irreducible variance.
Deep understanding of medical image data structures and the physical/clinical realities of imaging. Familiarity with image processing tools and building algorithms for medical imaging data.
Expert proficiency in Python and statistical data analysis ecosystems (e.g., pandas, scipy, statsmodels, seaborn/matplotlib). Proven ability with large, complex, and messy datasets.
Hands-on experience developing or fine-tuning deep learning algorithms (preferably using PyTorch) for computer vision tasks (segmentation, classification, detection) applied to medical images.
Demonstrated proficiency using modern agentic tools and LLMs (e.g., GitHub Copilot, Gemini, Claude) as a daily force multiplier to accelerate software development, rapidly prototype data solutions, and build reproducible pipelines.
Exceptional ability to distill complex, multi-dimensional data analyses into clear, strategic insights for cross-functional stakeholders.

Nice To Haves

Published research specifically related to domain generalization, image harmonization, or out-of-distribution (OOD) detection in medical imaging.
Experience working with large multi-vendor CT imaging datasets, with an understanding of acquisition and reconstruction protocols.
Proven track-record in diagnosing data- and annotation-related algorithm performance gaps, and designing data-driven solutions.
Experience with large-scale data querying and cloud storage (e.g., AWS, SQL).
Experience developing SaMD products and contributing to regulatory filings.
Experience with biostats to support FDA submissions.

Responsibilities

Build robust, reproducible analytical pipelines and visualizations over population-scale data, to characterise dataset distributions and model vulnerabilities across diverse patient populations.
Explore, develop, and validate methods for harmonizing complex data-related factors and image variations.
Translate findings about data variance and model behaviour into actionable data curation requirements, training-time robustness strategies, and architectural recommendations for downstream algorithm development.
Develop annotation protocols for algorithm training and validation for internal product development and FDA submissions.
Partner with Research Scientists, Machine Learning Engineers, Systems Engineers, Process Engineers, Product and Regulatory teams. Derive and present clear analyses from messy data to drive decision-making, and provide artifacts other functions consume.