You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
Readily

AI Engineer, Platform

  • Office
  • 0-3 years

Salary

$150,000 - 210,000/ year

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

About Readily

30% of U.S. healthcare cost is administration. We’re fixing that.

Readily is building the compliance layer for every healthcare company. Billion-dollar insurers and health plans turn to Readily to analyze regulations, conduct audits, and automate compliance research with AI.

We’re the fastest-growing company in this space - 10x revenue YoY. And we’re just getting started.

There’s an old Yorkshire saying: “Where there’s muck, there’s brass.” Healthcare compliance is messy. But in that mess lies an enormous opportunity. If you’re hungry to take ownership and build systems that matter, this is it.

Responsibilities

  • As an AI Engineer, you'll build the AI platform the rest of Readily ships on. That means the frameworks, shared services and tooling that let every engineer, from product to forward-deployed, build reliable LLM features fast, without reinventing retrieval, prompting or evals each time.
  • Your customers are our engineers, and through them, compliance teams at health plans, where an answer has to be right, cited and defensible to a regulator. You'll set the patterns, own the core abstractions, and measure success by how quickly and safely the team can ship AI to production.
  • Architect multi-agent systems. Design the frameworks that orchestrate foundation LLMs into compliance workflows like regulatory change analysis, gap analysis and audit prep, with abstractions product engineers can build on.
  • Build and optimize AI pipelines. Own retrieval over regulations, contracts and policies, prompting and context design, and make pipelines faster, cheaper and more accurate through caching, batching, parallelism, model routing and smarter retrieval.
  • Make every flag explainable and traceable. Build the mechanisms that tie each compliance flag back to the rule, example or source document behind it, so customers can defend it to a regulator.
  • Turn compliance rules into agent-ready logic. Build systems that translate regulations and contract requirements into structured logic paths agents can execute.
  • Close the feedback loop. Use user feedback and outcomes data to improve prompts, retrieval and workflows over time, and adapt them to each customer.
  • Own evaluation and monitoring infrastructure. Build the eval harness, release gates, tracing and dashboards that keep quality reliable and auditable across customer deployments.
  • Run the model layer. Build a gateway across providers with routing, fallbacks, caching, cost tracking and HIPAA-grade data handling.
  • Enable the team. Partner with product engineers to integrate AI through APIs, data pipelines and the frontend; work with compliance users to turn complex rules into workflows; write the SDKs, docs and patterns others build on.
  • Stay current on AI. Prototype new techniques and bring the ones that move our metrics into the platform.

Requirements

  • 1+ years building production software, including shared infrastructure, internal platforms or libraries that other engineers depended on.
  • Hands-on depth with LLM systems in production: RAG, tool use and agents, structured outputs, and the tradeoffs between models.
  • Strong Python and TypeScript, with a sharp sense for clean APIs and abstractions that are easy to use correctly.
  • A track record of optimizing LLM pipelines for latency, cost and accuracy, and an evals-first mindset: you trust metrics over demos.
  • Solid backend and infrastructure fundamentals: Postgres, queues and async jobs, cloud (AWS or GCP), CI/CD, testing and observability.
  • You multiply others. You write clear docs, give useful code review and enjoy unblocking teammates.
  • High ownership and speed in a small team, with the care to get details right in a high-stakes domain.
  • Experience: Any (new grads ok)
  • Visa: US citizen/visa only

Benefits

  • True founding-team ownership.
  • Career-defining experience: ship products that rewrite how the industry works.
  • Front-row to closing deals with billion-dollar enterprises
  • Hyper-growth environment (10× YoY - you’ll feel it).
  • A real chance to fix healthcare’s most expensive problem with AI.
  • Weekly pickleball + a team that loves to win together.
  • If you want true ownership and fix healthcare from its roots - we’d love to talk.

Where you’d work

From the office

The office

No visa sponsorship

You must already be able to work in the United States

About the company

Readily

  • Industry: HealthTech

Office in San Francisco, United States

Your chances

Worth a look before you spend an evening tailoring a CV for it.

  • 21 checks run
  • 1 red flag

Still hiring?

13 checks

No red flags

How crowded?

8 checks

1 red flag

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details13 facts · Role, Location, Compensation, Employment, Company
Tech stack
  • Python
  • PostgreSQL
  • AWS
  • CI/CD
Type
Full-time
Industry
HealthTech
Specialty
ML
Region
United States
Pay period
Annual
Show 7 more factsShow less

Role

Category
Data & Analytics
Specialty
ML
Experience
1+ years
Tech stack
  • Python
  • PostgreSQL
  • AWS
  • CI/CD

Location

Work model
Office
Region
United States
Office
  • San Francisco, United States
Visa sponsorship
Not sponsored
Must already work in
  • United States

Compensation

Salary
$150,000 - 210,000 / year
Pay period
Annual

Employment

Type
Full-time

Company

Industry
HealthTech

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason