Staff Data Scientist

About the Role

Accelerating clinical research is one of the defining challenges in healthcare. Promising therapies exist that patients can't access because the operational infrastructure to run clinical trials efficiently doesn't exist yet. We're building it. That means designing technology systems that bring order to a fragmented landscape of clinical data sources, automating the operational work that slows trials down, and turning real-world clinical data into a foundation for predictive intelligence.

We're looking for a Staff Data Scientist to be the person who understands our data deeply enough to know what's possible and curious enough to prove it. We have a truly unique data set within the industry, connecting clinical data (emr, endoscopic video, etc…) to trial data across 80+ trial sites. We're looking for someone who wants to dig deeply into this data - to understand its structure, its gaps, what it can tell us - and connect that understanding to real outcomes for sites and patients. The landscape is evolving rapidly, and the right person will have a point of view on how to apply new capabilities to our specific data and problems as they emerge.You'll work hands-on with the data, structure experiments, evaluate what's modelable, and directly influence what we build and how. This role sits at the intersection of data science, product strategy, and ML: you'll lay the foundation for our predictive capabilities and shape what that function becomes.

This is an opportunity for someone who wants to be part of a small, fast-moving engineering team at a formative stage. You'll shape what gets built, how decisions get made, and what the team becomes.

Responsibilities

• Work with clinical, video, and clinical trial operational data to understand what's there, what's meaningful, and how we can use it to drive a more efficient clinical trial system
• Design and run experiments that determine what's worth building
• Stay close to the evolving ML and model landscape and bring a point of view on how new capabilities apply to our data and problems
• Define the path from raw data to product and operationalization: what to model, how to evaluate it, and when it's ready to ship
• Partner with product and engineering to translate findings into concrete product decisions
• Identify opportunities where our data creates unique predictive advantages
• Evaluate where we should build, where we should partner, and where existing approaches fall short
• Help shape the engineering culture of a small, growing team: how technical decisions get made, how problems get debated, what rigor looks like in practice

What We’re Looking For

Required Qualifications

• 5+ years of experience in data science, applied ML, or quantitative research, with significant time spent hands-on with data
• Experience with healthcare data, clinical research, or life sciences
• A deep curiosity to understand data and connect it to the real world
• Deep experience designing and running experiments: you know how to structure a question, test it honestly, and draw conclusions that hold up
• Strong statistical foundations and the judgment to know when a result is meaningful versus interesting
• Fluent in Python and SQL, comfortable working across the data stack from exploratory analysis through to production-ready pipelines
• Experience working across data science, product, and engineering: you can influence what gets built, not just analyze what exists
• Have worked with complex, messy, real-world data and know how to make it useful without pretending it's clean
• Knowledgeable about ML capabilities and frameworks, with the judgment to know when something is genuinely applicable versus hype
• Can communicate findings clearly to technical and non-technical audiences, and make a persuasive case for what to build next

Preferred Qualifications

• Experience working at growth stage startups (strongly preferred)
• Experience with medical imaging or video data
• Familiarity with clinical trial operations, disease classification, or patient identification problems
• Experience building or defining the roadmap for an ML function from early stages
  • A track record of data science work that directly changed product direction