Docflow builds AI agents that run the back office for healthcare providers. Our automation handles the work that buries their teams: document intake, prior authorizations, order entry, and payer portal workflows. Customers start with a paid pilot, see real work getting done within weeks, and expand from there.
We're a small, scrappy, AI-native founding team, and we're growing fast. Every customer we sign runs live workflows that have to keep working, and there are more of them every month. That's why we're hiring you.
The Role
This is an engineering role that lives where the product meets the customer. You'll stand up new customer workflows alongside our sales team, keep the live ones healthy, and own the systems that make both of those faster every month.
Here's how we work, and it's the most important thing to understand about this job: we do the work manually first, then we automate it. When a workflow needs fixing, you fix it. Then you ask the real question, which is how to make that fix faster next time, or unnecessary, or something the customer can do for themselves. We expect you to keep scaling yourself, handling more and more by building systems behind you. The person who does well here is constitutionally incapable of doing the same manual thing twice without trying to automate it.
You'll also own our QA product. An agent reviews production runs against each workflow's requirements and flags the ones that fall short. You'll review its verdicts, accept or reject what it files, and then make the agent better at its job. That loop is this role in miniature: do the judgment work yourself, then teach the system to do more of it.
To be clear about what this isn't: it's not a support queue in the help desk sense, it's not a pre-sales demo role, and it's not a consultant embedded at a customer site. You'll write and review real code every week, from our office, with the rest of the team.
What You'll Do
Build out new customer workflows with the account executive who owns the account. They stay in the lead and bring you what the customer needs; you make it real. We want this as close to real time as possible, and making it faster is part of your job, not a nice-to-have
Support live customer workflows: fix what breaks, then remove the reason it broke
Own our QA product, from reviewing what the agent flags to making the agent sharper
Own how workflow changes get published: make sure deployments do what they're supposed to, catch the changes that shouldn't ship, and roll back cleanly when something is wrong
Watch for patterns. A workflow that keeps needing the same fix is telling you something upstream is wrong, and chasing that down is worth more than closing the ticket
Build the tooling, checks, and guardrails that make everything above take less time every month
Learn our customers' industry well enough to argue with how they describe their own process
What We're Looking For
Must have:
Real professional software engineering experience. You'll write and review production code every week, and defend the business logic you wrote.
Strong TypeScript, or strong experience in a comparable typed language plus the appetite to get to strong TypeScript quickly.
The ability to read unfamiliar code fast. Much of what you touch was written by someone else, or by an agent.
An instinct to automate your own work. This is the single most important trait for this role. Doing the manual version first is the job; leaving it manual is not.
Genuine interest in complicated real-world processes. Prior authorization rules, billing codes, payer-by-payer exceptions that exist for reasons nobody ever wrote down. If a twenty-step workflow that nobody has documented sounds tedious rather than interesting, this will be a frustrating job.
A customer-centered instinct. The account executive owns the customer relationship and stays in the lead, so you won't be on every call. But every judgment call you make comes down to what this looks like to the person whose order it is.
Comfort in a company of four to six people, where the job is whatever it takes and you'll largely define your own benchmarks as you go.
Willingness to work in-office five days a week, and to be around some evenings and weekends when something critical breaks.
Preferred:
Forward deployed, solutions, implementation, or product engineering experience where you also wrote production code
Experience in healthcare, revenue cycle, insurance, or another domain with dense rules you had to learn from scratch
Experience with durable workflow orchestration, browser automation, or long-running job systems
You use AI coding tools yourself, such as Claude Code, Codex, or Cursor, to move faster
Based in Los Angeles, or ready to be
We'll teach you the industry. We can't teach you to find it interesting.
Compensation and Benefits
Base salary of $150,000 to $185,000 depending on experience
Founding-team equity
Health insurance