Requirements
- 5+ years in software engineering
- At least 1 year shipping LLM-powered products in production
- Strong in Python and/or TypeScript; comfortable across APIs and data, with enough frontend to finish a feature
- Hands-on with prompting, function calling, RAG, structured outputs and agent orchestration
- Experience designing evals and using data to decide what to fix next
- Product sense: cares whether the patient got their appointment, not just whether a metric moved
Benefits
- Equity
Skills
Nice to have
Full job description
Senior Software Engineer, AI Agents | Healthcare Voice AI
Our client is a healthcare AI company building conversational agents that ease the staffing crunch and paperwork load on clinical teams. Their agents hold real phone conversations with patients every day, handling scheduling, billing questions, prescription refills and post-discharge follow-ups for hospitals, medical groups and community health centres.
You’ll own agents from first conversation design through to production, then use live patient conversations to make them better.
- Design, build and ship AI agents end to end: conversation flows, prompts, tool calling, retrieval, memory and the backend services behind them
- Build the evaluation system (offline tests, simulated conversations, human review and production monitoring) that every agent change has to pass before release
- Improve instruction following, tool-calling reliability, latency and cost across the LLM and speech stack
- Dig into real conversations and failure cases, then fix what you find in the prompt, tools, model or product
- Help shape the next-generation voice agent platform and choose the right models for each task
- Work with product, clinical and customer teams to turn real care workflows into dependable agent behaviour
What’s in it for you:
- Real ownership: put several production agents in front of patients with health system partners in your first three months
- A mission that matters: making healthcare work better for the people who use it
- A small team with direct access to senior engineering leadership, where your work ships fast
- Real conversation data to learn from every day, not a research seat
$160-210k | Hybrid, NYC or SF
Who you are:
- 5+ years in software engineering, including at least a year shipping LLM-powered products in production
- Strong in Python and/or TypeScript, comfortable across APIs and data, with enough frontend to finish a feature
- Hands-on with prompting, function calling, RAG, structured outputs and agent orchestration
- Experience designing evals and using data to decide what to fix next
- Product sense: you care whether the patient got their appointment, not just whether a metric moved
- Clear communicator with engineers, clinicians and executives alike
- A plus: voice AI (speech-to-text, text-to-speech, turn-taking, telephony), healthcare or other regulated-industry experience (HIPAA, FHIR), or workflow orchestration experience
If you want to look back in a year and know that patients talk to something you built every single day, let’s talk.
Apply below or reach out directly at Julia at Alldus dot com.
Opens Alldus’s listing on LinkedIn in a new tab.