Senior Software Engineer, AI

Tono Health builds software and operations for specialty care, starting with dermatology. The Senior Software Engineer, AI will build production AI agents for clinical and operational workflows and develop shared agent infrastructure, evaluation systems, and reliability safeguards.

Responsibilities

• Own 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
• 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

Preferred

• 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
• Agent Frameworks
• Mastra
• LangGraph
• Durable Workflow Tools
• Inngest
• LoRA
• Fine-Tuning
• Startup Experience
• Healthcare Experience
• Regulated Industry Experience
• Multi-Tenant Systems

Benefits

• Meaningful equity in a high-growth, venture-backed company
• Medical, dental, and vision coverage
• Direct access to founders and an agile team where your impact is highly visible
• Weekly demos with leadership
• Unlimited PTO to recharge when you need it
• Hybrid work, currently a few days per week in the DUMBO, Brooklyn office; fully remote considered for the right candidate

Company

• AI-native platform for specialty dermatology care
• New York, New York, USA
• https://tonohealth.com/
• Founded in 2020
• 11-50 employees

Qualifications

• 5+ 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
• 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

Required skills

• Agent Feedback Loops, Database Schema Design and Migrations, Feature Flags, LLM Evaluation, LLM Tool Calling, Monitoring, PostgreSQL, Production LLM Agent Development, Retries and Fallbacks, Structured Outputs, TypeScript

Experience

• 5+ years