Back to jobs

AI Engineer, Decision Intelligence

Pay
Pay not listed
Work setting
On-site — work setting source
Work setup in the employer’s posting: IN_OFFICE
From the employer’s posting
Employment
Full-time — employment source
Employment type in the employer’s posting: FULL_TIME
From the employer’s posting

What you’ll work on

Full posting
  • Build the decision engine that chooses which claims to contest and at what offer amount

  • Design LLM systems that generate dispute arguments and full submissions

  • Build golden datasets, offline evals, and measurement for every change

  • Close the feedback loop from arbitration outcomes back into the system

  • Split work between deterministic rules and model reasoning, and explain the line

From the employer’s posting
Build the decision engine that determines which claims to contest and at what offer amount
Design the LLM systems that generate arguments: medical necessity, patient acuity, market comparables, the full submission
Build evaluation infrastructure. Golden datasets, offline evals, and the ability to know whether a change actually improved outcomes
Close the feedback loop from arbitration outcomes back into the system, so every decision makes the next one better
Architect the split between deterministic rules and model reasoning, and defend where you drew the line

What you’ll bring

All qualifications

Core experience

  • 5+ years engineering, with meaningful recent time building LLM-powered or ML-driven products in production

Preferred experience

  • Experience building in regulated or security-sensitive environments (HIPAA, SOC 2, PCI, financial controls) is a plus
Qualification wording
5+ years engineering, with meaningful recent time building LLM-powered or ML-driven products in production
Experience building in regulated or security-sensitive environments (HIPAA, SOC 2, PCI, financial controls) is a plus

About recoursehealth-com

Recourse is being built in partnership with 25M Health, a healthtech venture firm.

In the employer’s words · Read in context

Apply at recoursehealth-com

Posting record

Report an error

Actively hiringFirst seen by us 1 day ago, still listed, and not a repost of an earlier posting.

Status in our records
Live
First seen by us
Nov 18, 20261 day ago
Recorded sightings
2
Last seen by us
Nov 19, 2026

These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.

How this job compares

Time since we first saw it

Day 1

Similar jobs usually come down between day 1 and day 14.

From 1,249 similar postings that came down. Coming down is not always a hire.

recoursehealth-com is hiring

3 open jobs

Open jobs by the week we first saw them, last 12 weeks.

Hiring record

See how this role fits your experience

Add your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.

  • Python
  • TypeScript
  • PostgreSQL
  • GCP
Where the posting names them
- Strong instincts for where probabilistic reasoning helps and where it introduces unacceptable risk - Comfort with TypeScript or Python. The specific stack matters less than the ability to pick things up - Experience building in regulated or security-sensitive environments (HIPAA, SOC 2, PCI, financial controls) is a plus
- Partner with operations and payer strategy, who see patterns in the claims before the data does We build with Claude Code daily and run a Codex review pass on every slice. The stack is TypeScript, Next.js, Prisma, and PostgreSQL on Google Cloud, with LLM reasoning throughout. Who You Are

Your next step

Complete your application on jobs.gem.com. The employer’s form will show what is required.

Already applied? Track this application

Job description

View original posting ↗

Every dispute is one move in a repeated game against an adaptive opponent. Build the system that gets better at playing it.


Why This Exists


A federal arbitration system called Independent Dispute Resolution, or IDR, now determines billions of dollars in healthcare payments each year. Providers win the vast majority of disputes, yet most eligible claims are never filed. The process is manual, fragmented, and resource-intensive, and most providers don't have the infrastructure to pursue what they're owed.

The No Surprises Act created the framework, and the market already exists. Today it runs on spreadsheets, consultants, and static playbooks. We're building the first intelligent system designed to operate inside it.

Automating the paperwork is table stakes. The interesting part is the second half: IDR is baseball-style arbitration, where each side submits one number and an arbitrator picks one. No splitting the difference. That means every submission is a bet, and every outcome is a signal about how to bet better next time.

This role owns that.


Why This Is Hard (and Interesting)


You're building a decision system in an adversarial, regulated, sparse-data environment.

The same payers appear repeatedly and they change behavior when they notice patterns. Arbitrators rotate and have their own tendencies. Regulations shift under you. You have to make a call on every claim before you have statistically comfortable data, and being wrong costs a provider real money.

The system also has to be defensible. When a customer asks why we submitted a particular number, "the model said so" is not an acceptable answer. You need reasoning you can explain to a hospital CFO.

Concretely: which claims to contest, what to offer, what evidence to include, how to write the argument, and how all of that should change based on the payer, the arbitrator, the procedure codes, and everything we've learned so far. Deterministic rules and LLM reasoning both have a role. Figuring out which does what is your call.


Who We Are


Recourse is being built in partnership with 25M Health, a healthtech venture firm. We have institutional backing, a shared platform team spanning engineering, strategy, design, and back-office, and early access to large provider systems.

We are actively filing disputes for real customers, including a large multi-facility health system and a litigation-finance partner with hundreds of millions in claim value. This is a funded, validated opportunity with real customers and real data.

We are a small, nimble team. We move quickly and we value clarity over theater. We want this to be the best work of your career. The stretch you look back on as the one where you shipped real things, with people who raised your game, on something that mattered.

We care about clear thinking, high ownership, intellectual honesty, and direct communication. We believe operations, product, and engineering should operate as one pod, not three functions. We want the machines to do machine work, and the humans to do their best work.


The Role


You'll own the intelligence layer of the product. You will:

  • Build the decision engine that determines which claims to contest and at what offer amount
  • Design the LLM systems that generate arguments: medical necessity, patient acuity, market comparables, the full submission
  • Build evaluation infrastructure. Golden datasets, offline evals, and the ability to know whether a change actually improved outcomes
  • Architect the split between deterministic rules and model reasoning, and defend where you drew the line
  • Close the feedback loop from arbitration outcomes back into the system, so every decision makes the next one better
  • Build for explainability. Every recommendation needs reasoning a customer would accept
  • Partner with operations and payer strategy, who see patterns in the claims before the data does

We build with Claude Code daily and run a Codex review pass on every slice. The stack is TypeScript, Next.js, Prisma, and PostgreSQL on Google Cloud, with LLM reasoning throughout.


Who You Are


You've shipped LLM systems that people depend on. Not demos. Production systems with evals, guardrails, and a real answer for what happens when the model is wrong.

You think about systems, not prompts. Prompt engineering is a component. The interesting work is architecture: what's deterministic, what's learned, how they interact, and how the whole thing improves over time.

You're rigorous about evaluation. You know that "it seems better" isn't evidence. You build the measurement before you build the feature.

You are AI-pilled and current. The landscape moves monthly. You track it because you want to see the next shift before anyone else, and you have opinions about what's real versus hype.

You have a bias to action. You don't default to no. Speed of iteration over polish of iteration. You start, you learn, you fix things in motion. Most decisions are reversible and do not need extensive study.

You are intellectually honest. You seek out evidence that disconfirms your approach. You say so when you're wrong. You use plain language. You respectfully challenge decisions you disagree with, and once a decision is made, you commit.

You put the team first. You are reliable and fully invested. You take your vacations. You check on your teammates. You help build a culture where people do their best work because they are supported, not squeezed.


What You Bring


  • 5+ years engineering, with meaningful recent time building LLM-powered or ML-driven products in production
  • Real experience with evaluation: building golden datasets, running offline evals, measuring whether changes helped
  • Comfort across the stack. You can ship the thing end to end, not just the model layer
  • Strong instincts for where probabilistic reasoning helps and where it introduces unacceptable risk
  • Comfort with TypeScript or Python. The specific stack matters less than the ability to pick things up
  • Experience building in regulated or security-sensitive environments (HIPAA, SOC 2, PCI, financial controls) is a plus
  • A preference for small teams and early-stage chaos over mature org charts

Strong plus, not required: healthcare data, claims, or any adversarial decision domain (fraud, risk, pricing, trading). If you have it, you'll move faster. If you don't, we'll teach you.

Sound judgment, technical depth, and ownership mindset are required. Grit matters more than pedigree.


Why This Role


Most applied AI jobs are wrapping a model around an existing workflow. This one is different: the intelligence is the product, the feedback loop is real and measurable, and the outcome is dollars recovered rather than an engagement metric.

You'd also be first here. Nobody in this market has built a genuine decision-intelligence layer on arbitration outcomes. The data exists and almost nobody is doing the work. You'd have unusual latitude to decide what this becomes.

If you want this to be the most memorable stretch of your career, where you shipped something real, with a team you respected, in a domain that actually matters, this is the seat. Please apply even if you don't fit 100% of these requirements. We would like to talk.


Equal Opportunity


Recourse is an equal opportunity employer. We do not discriminate on the basis of race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, veteran status, or any other characteristic protected by law. We believe the best teams are built from people with different backgrounds and perspectives, and we're committed to creating an environment where everyone can do their best work.

About the role

We file this job under AI Engineer, by the work the posting describes.

AI engineers build products on top of AI models that already exist, most often large language models: they connect a model to a company's data and tools and ship the assistants, agents and search features people use.

Postings ask for strong Python or TypeScript, experience with model APIs, retrieval and agent frameworks, and ways to test whether the model's answers are good enough.

An ML engineer trains and serves models; an AI engineer usually starts from a model someone else trained and builds the product around it, though titles often mix the two.

Source details

View original posting ↗

Source notes

Source excerpts

Selected passages from the saved posting. Check the full description for conditions and exceptions.

Pay

No pay amount identified in the saved description.

Location & working pattern

San Francisco, CA

Working pattern and location restrictions need checking in the full posting.

Work authorization

No clear work-authorization passage found. Eligibility is unconfirmed.

Find answers in the posting

AI
How answers work

AI selects complete passages from this posting. Check them for conditions and exceptions.

Uses this posting and your question. No profile needed.