Senior Software Engineer, AI

About this role

About TonoSpecialty care is hard to access and even harder to run. Patients often wait months, and clinics rely on fragmented tools and manual workflows. Tono builds software and operations together to make specialty care faster to access and easier to deliver, starting with dermatology. We’re building a fully autonomous specialty medicine clinic: continuous, real-time care for patients anywhere. What makes us different is how we build. We run two clinics of our own, a national telehealth practice and an in-person clinic in DUMBO, Brooklyn. Our engineers work side by side with our doctors and care coordinators to build (mostly) every piece of the software from scratch. The long-term goal is for specialty clinics across the country to run on our autonomous EHR, freeing them from the administrative burden that slows care down. Today we see patients in 33 states, covering more than 80% of the US population. You will work closely with the co-founders and a team of engineers and physicians (backgrounds include Amazon, Apple, and leading academic medical centers). We are backed by Village Global (backed by Mark Zuckerberg, Jeff Bezos, Michael Dell, chaired by Reid Hoffman), HOF Capital, and Oncology Ventures. What You'll DoOwn the agents that run Tono's clinic end to end. You'll design, build and ship AI agents that handle real clinical and operational work, such as drafting clinical notes, triaging intake, coordinating care, and automating the admin work that slows doctors down. You'll work in our TypeScript monorepo (Cloudflare DO, tRPC, Prisma, Postgres, Inngest) alongside the engineers, physicians and care coordinators who use what you build. You'll also build the foundation other engineers build on: shared agent infrastructure, tool and memory abstractions, durable workflows, tracing, and the evaluation harnesses that tell us whether an agent is actually getting better. On any given week you might be: Building an agent that turns a patient visit into a structured clinical note a doctor trusts

Designing evals and labeled datasets from real clinician feedback, then using them to catch regressions before they ship

Building self-improving loops where physician corrections flow back into prompts, retrieval and fine-tuning

Adding guardrails, human-in-the-loop review and safe fallbacks so an agent fails gracefully

Debugging why an agent did something unexpected, using traces, logs and replay

We build AI that has to be reliable in production. That means structured outputs, evaluation loops, monitoring and clear escalation to a human when it matters. How We WorkWe ship quickly, with discipline: small PRs, clear ownership, and tight feedback loops.

Small team, broad scope. Engineers regularly work across frontend, backend, data, and infrastructure.

We ship with confidence in a regulated environment: feature flags, careful reviews, and safe migrations (including backfills). We use AI all the time but we do not vibe code our way into debt. Patients and doctors deserve better.

We invest in maintainability. Dependency upgrades, performance work, and removing dead code are part of the roadmap.

Observability is built-in. Logs, metrics, alerting, and error monitoring are part of the job.

We value builders. Curiosity, good taste, and a willingness to pick up whatever the system needs goes a long way.

StackFrontend: Next.js, TanStack Start, React Backend: Fastify, tRPC, Prisma, PostgreSQL Durable Workflows: Inngest AI: Mastra, Flue, OpenAI, Anthropic, Vertex Infra: Cloudflare, Turborepo, Doppler, AWS, GCP Observability: Posthog Data: Motherduck/DuckDB, dbt, dlt, Prefect, BigQuery What We're Looking For5+ years of software engineering experience, with strong TypeScript across frontend and backend

Hands-on experience building and shipping LLM-powered agents in production, not just prototypes

Experience designing evals: test sets, LLM-as-judge, regression suites, and tying quality metrics to real outcomes

A practical sense of making LLMs reliable: structured outputs, retries and fallbacks, tool-calling design, and monitoring

Experience with data-labeling techniques and feedback loops that improve an agent over time

Solid relational database fundamentals (Postgres, schema design, migrations)

Comfort shipping iteratively with feature flags, instrumentation and tight feedback loops

The ability to take an ambiguous problem, break it down, and drive it to done

Care about code quality and take pride in your craft

Nice to have: experience with agent frameworks such as Mastra or LangGraph, durable workflow tools such as Inngest, LoRA or fine-tuning, and startups, healthcare, regulated industries or multi-tenant systems

Compensation & BenefitsSalary: 180k - 275k commensurate with experience Equity: Meaningful equity in a high-growth, venture-backed company Medical: Medical, dental, and vision coverage Growth: Direct access to founders and an agile team where your impact is highly visible. We do weekly demos with leadership PTO: Unlimited PTO to recharge when you need it LocationNew York City preferred. We are hybrid and currently spend a few days per week in our DUMBO, Brooklyn office. We will consider fully remote for the right candidate.