Senior AI/ML Engineer

Metriport; United States; On-site; USD 140,000 - 210,000; Full time

Job summary

Metriport is seeking its first Machine Learning Engineer to own ML end-to-end—from framing the problem with customers, to training models, to serving them in production and keeping them honest. You will work with rich, longitudinal clinical datasets and apply both traditional ML methods and modern deep learning where appropriate.

You’ll ship production models for healthcare data, ensuring robust evaluation, monitoring, and retraining.

Responsibilities

• Builds models on clinical data at scale: risk stratification, utilization prediction, care-gap detection.
• Owns full ML lifecycle from problem framing to production, monitoring, retraining, and maintenance.

Job description

About Us

Medical data exchange is one of the biggest unsolved problems in US healthcare. If you've spent any real time in the healthcare system, you've felt it, and it only gets worse the sicker and older you get. Metriport exists to fix that. We connect to the data sources the healthcare providers of tomorrow need, take raw data that's unusable in its source form, and turn it into a single clean format that care teams, and their agents, actually use to improve outcomes. Record retrieval across thousands of legacy systems and antiquated data pipes that used to take weeks now takes seconds. Clinicians walk into appointments with the full patient picture already in hand, and that speed can mean spotting a condition early enough to actually treat it.

We're not a healthcare company. We're a technology company that happens to operate in healthcare, and we build every layer ourselves: connect, transform, and insight. Legacy EHRs were built to get providers paid, not to serve the clinical experience. We're building what should have existed instead: the system of record for all of US healthcare. We started in data exchange. Today we compete with the largest data platforms in the space. Tomorrow we will be the infrastructure layer healthcare runs on.

We've raised $28.4 million from top-tier VCs (including Matrix, ARTIS and Y Combinator), found product-market fit (multi-million dollar ARR, 100+ customers including Amazon One Medical, Circle Medical, Color Health, and Strive Health), and have years of runway ahead of us. If you've had a good healthcare experience in the past few years, there's a good chance Metriport was behind it. That's the version of healthcare we want people to not just expect, but demand. Join us and build the future.

About You

We're a small, high-output team, mostly former founders including YC alumni, and we operate with real autonomy and almost no bureaucracy. We hire based on competence, not pedigree. Leaders are in the office six days a week, and we generally expect the team to be available six days a week too. Not because we count hours, but because there's always more wood to chop when revolutionizing how tomorrow's healthcare providers deliver care to their patients today. We trust our team to take the time off they need and we've never said no to a time off request.

You have an entrepreneurial mindset and a strong sense of ownership. You don't wait to be told what's broken. Instead, you believe you can figure out any problem that lands in your lap even outside your exact domain. When someone scopes something for three weeks, you ask why it can't be done in three days, and you also know the difference between shipping a fast v0 and cutting a corner that comes back to bite you. You walk the tightrope between craft and speed without falling off either side.

The role

This is the first Machine Learning Engineer role at Metriport. We have access to the richest clinical datasets in the country - longitudinal medical records for hundreds of millions of individuals - and we've barely scratched the surface of what can be learned from it. You'll own machine learning at Metriport end-to-end: from framing the problem with customers, to training the models, to serving them in production and keeping them honest.

This is applied ML on messy, high-dimensional, real-world healthcare data - not a research role, and not an LLM-wrapper role.

You have deep ML fundamentals, from classical methods through deep learning. You can take a prediction problem from a linear baseline to gradient-boosted trees to a neural network - and you know when each one is the right answer.

You've shipped models to production and lived with them: you have opinions about evaluation, monitoring, retraining, and what can break after launch.

You're deeply experienced with ML, but still have strong eng chops: you can stand up a service, write the IaC, instrument it, and own it end-to-end. Pythonis home; TypeScript, AWS, and SQL aren't going to scare you.

You're pragmatic about LLMs. You've used them where they win and you know where a smaller, cheaper, more reliable model wins instead.

You're comfortable with messy real-world data: sparse, inconsistent, high-dimensional, and full of surprises. Healthcare data is all of these at once.

You're entrepreneurial-minded with an olympian-level work ethic (about half our engineering team are former founders).

When someone scopes a project for 3 weeks, you ask "why can't it be done in 3 days?" - and you help others develop that same instinct.

You're a hacker at heart, with a good sense of which rules should, and shouldn't, be broken.

What you'll be doing

You'll build the models, and the ML platform underneath them, that turn raw clinical data into intelligence our customers act on.

Day to day, that looks like:

• Building predictive models on clinical data at scale: risk stratification, expected utilization / prediction, care-gap detection.
• Owning the full ML lifecycle: problem framin