Founding Engineer, AI Agents

Shasta Health
Shasta Health

Software Engineering, Data Science · Full-time

San Francisco, CA, USA

Posted on Nov 17, 2026

Shasta Health builds AI agents that help healthcare practices get patients into care. Our agents answer calls, schedule appointments, verify insurance, and follow through on the administrative work that slows practices down.

We built Shasta after running our own physical therapy practice and doing this work ourselves. We know what happens when a patient can’t get through, an insurance check holds up scheduling, or the front desk spends its day chasing paperwork. Today, hundreds of clinics use Shasta to handle this work.

We’re hiring a founding engineer to work directly with the founders, expand what our agents can do, and help shape how we build.

The role

You’ll work directly with clinic teams to understand their needs, build solutions, and see your work used in day-to-day operations. You’ll own projects from the first customer conversation through design, development, and production.

This is a full-stack role spanning voice agents, phone systems, LLM orchestration, computer-use agents, and the interfaces customers use to work with them. You’ll help set the technical direction and engineering practices as the team grows.

How we work

This is an in-person role. We’re an early-stage startup with ambitious goals, and we work at an intense pace. Expect a demanding workload.

You’ll own meaningful parts of the product and make decisions that shape how the company grows.

You’ll learn by shipping systems into real clinics, working directly with customers, and seeing the results of your decisions firsthand.

What you’ll do

  • Own new workflows from understanding a clinic’s needs through designing, shipping, and operating the solution.
  • Build AI agents that complete tasks across phone calls, SMS, APIs, and browser automation.
  • Build reliable browser agent infrastructure that works across healthcare EMRs and portals, improving speed, handling failures, and verifying that tasks were completed correctly.
  • Build and operate reliable phone and fax systems.
  • Build interfaces that help clinic teams configure agents, review their work, and step in when needed.
  • Design evaluations and observability tools to measure task success, diagnose failures, and improve agent reliability.
  • Make technical decisions and establish engineering practices that help a small team ship quickly and operate dependable systems.

Your first 90 days

  • By 30 days: Ship improvements to production while learning our codebase, clinic workflows, and how our agents operate.
  • By 60 days: Own a system end to end, from technical decisions and development through deployment, monitoring, and reliability.
  • By 90 days: Own a product area, working directly with customers to decide what to build, ship it, and measure its impact on clinic operations.

What we’re looking for

  • Strong software engineering fundamentals, with depth in backend or full-stack development. We care more about what you’ve built and how you approach difficult problems than your credentials or experience with a particular programming language.
  • Ability to experiment, ship, and learn quickly while building systems customers can depend on.
  • Experience shipping and operating production systems.
  • Comfort owning ambiguous problems and deciding what to build.
  • Hands-on experience building AI agents is required. Professional, personal, and hobby projects all count. You’ve built an LLM-powered agent that uses tools or APIs to complete multi-step tasks, and can walk us through what you built, how you tested it, and how you handled failures.
  • Clear written and verbal communication. Everyone at Shasta works directly with customers.

Particularly relevant experience

Any of the following would be helpful, but none is individually required:

  • Early-stage startup experience or meaningful ownership of a product from zero to production
  • Conversational AI, telephony, or real-time communication systems
  • Messaging systems and conversational interfaces
  • Healthcare EMRs, insurance eligibility, prior authorization, or revenue-cycle operations
  • Background jobs, queues, and durable workflows
  • LLM evaluation, observability, and agent reliability