AI Synthetic Healthcare Record Generator

Telvion Labs

Remote · $130k – $160k / year · Contract · Posted 3 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

We're building the next generation of privacy-preserving healthcare research tools, and hospital data partners keep asking for one thing we don't yet offer: statistically faithful synthetic patient records they can share freely with researchers. You will design generative models that produce synthetic electronic health records preserving clinically meaningful correlations, longitudinal patterns, and rare-condition distributions, while passing rigorous re-identification risk audits. This six-month engagement reports directly to our research lead and includes co-authorship opportunities on benchmark papers we plan to publish with two academic medical center partners.

Fully remote.

Responsibilities

Design generative models producing synthetic EHR data with realistic longitudinal structure
Build and run re-identification risk audits against generated datasets
Benchmark synthetic data utility against real held-out clinical datasets
Collaborate with academic medical center partners on benchmark publications
Document generation assumptions and known limitations for downstream researchers

Requirements

5+ years working with generative models or synthetic data techniques
Strong Python, PyTorch, and applied statistics background
Prior exposure to healthcare data structures (EHR, claims, or clinical trial data)
Comfortable working under HIPAA-adjacent data handling constraints