Senior Software Engineer - Voice AI Platform
parlanceWoburn (MA)
Senior Software Engineer - Voice AI Platform
Posted 11 days ago
parlanceWoburn (MA)
SENIORITY
Senior
About the role
Senior Software Engineer – Voice Ai Platform Parlance builds conversational voice AI for healthcare — patient-facing agents that answer calls, verify identity, schedule, and reach into EHRs like Epic, Cerner, Meditech, and Athena to get things done. We are looking for a senior full-stack engineer who has shipped on a modern voice agent stack and can own problems end to end: from telephony and real-time media, through orchestration and LLM logic, to the APIs and data services behind it. This is not a narrowly scoped integrations role. You will be one of the engineers shaping how our next-generation voice platform is built.
What You'll Do:
Design and build real-time voice agents on frameworks such as Pipecat, LiveKit Agents, or comparable platforms — STT/TTS pipelines, turn-taking, interruption handling, latency tuning Own features across the stack: telephony/CCaaS connectivity (SIP, WebRTC, Five9/Webex CC), backend services in Python, and the internal tools and dashboards the team runs onBuild and extend the services that connect agents to healthcare systems — FHIR-based EHR integrations, scheduling, and patient data access — with the security and reliability healthcare demands Debug hard problems in production: audio quality, call flow failures, model behavior, and distributed-system issues across cloud, telephony, and third-party APIsSet up evaluation and observability for voice agents so we know when they are working and when they are not Contribute to architecture decisions, review code, and raise the bar for the team Work directly with product, customer success, and customers to turn ambiguous requirements into shipped software
What We're Looking For:
- 6+ years building production software, with strong depth in Python and comfort across backend, frontend, and infrastructure
- Hands-on experience building voice agents on Pipecat, LiveKit, Vapi, Retell, Daily, or a similar real-time framework — you have dealt with barge-in, latency budgets, and flaky audio, not just a demo
- Working knowledge of real-time media and telephony: WebRTC, SIP, audio codecs, streaming STT/TTS (Deepgram, ElevenLabs, Cartesia, Azure Speech, or similar)
- Experience integrating LLMs into production systems — prompt design, function calling, structured outputs, evals
- Solid engineering fundamentals: API design, testing, CI/CD, containers, cloud deployment (Azure preferred; AWS/GCP fine)
- Strong debugging instincts and the ability to work through ambiguity without waiting for a spec
- Clear written and verbal communication
Nice To Have:
- Healthcare integration experience: FHIR, HL7, EHR APIs, HIPAA-aware engineering
- Contact center platform experience (Five9, Genesys, Webex CC, Amazon Connect)
- Experience with CCaaS/IVR migration or replacing legacy speech platforms
- Frontend experience with React/TypeScript for Web PortalWhy Parlance
Small, senior engineering team with real ownership. Real patients on the other end of every call. Backed by Constellation Software, so the stability of a large company with the pace of a small one.
Compensation & Eligibility
Candidates must be authorized to work in the United States; we are unable to sponsor employment visas now or in the future.
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.