Senior Software Engineer, Agents

Ellipsis Health • New York, NY

3d • $160,000 - $210,000

About The Position

Ellipsis Health builds AI products that address healthcare staffing shortages and administrative burden. Its conversational AI and patented voice biomarker technology support patient interactions such as scheduling, billing questions, medication refills, and post-hospital check-ins.

The Senior Software Engineer will join the provider engineering team to build AI agents used by health systems, provider groups, and FQHCs. The role partners with product, clinical, deployment, commercial, and customer teams to take agent workflows from concept to production. It is a hands-on, full-stack AI role encompassing conversation design, prompts, tool calling, evaluations, APIs, and production data. The engineer will use live conversation data to improve agent quality, safety, speed, and reliability.

In the first three months, the engineer is expected to ship multiple production agents with health system partners, build an evaluation suite required before agent changes ship, and measurably improve agent performance in production. The position works directly with the SVP of Engineering and engineering leads on a small team.

Requirements

• At least 5 years of professional software engineering experience, including at least 1 year building and shipping LLM-powered applications in production.
• Strong proficiency in Python and/or TypeScript; comfort with backend APIs and data, and sufficient frontend capability to ship a complete feature.
• Hands-on experience with prompting, tool use and function calling, RAG, structured outputs, and agent orchestration.
• Experience designing evaluations and using data to determine what to improve.
• Product sense and focus on patient outcomes.
• Clear written and verbal communication with technical and non-technical teammates.

Nice To Haves

• Voice AI or real-time speech experience, including STT, TTS, voice activity detection, turn-taking, and telephony such as Twilio, SIP, or WebRTC.
• Fine-tuning or post-training experience with open or hosted models.
• Experience in healthcare or another regulated environment, including HIPAA, EHR, and FHIR.
• Experience with workflow orchestration such as Temporal.
• Familiarity with LLM observability and tracing tools.

Responsibilities

• Design, build, and ship AI agents end to end, including conversation flows, prompts, tool and function calling, retrieval, memory, and supporting backend services.
• Build evaluation systems, including offline test suites, simulated conversations, human review loops, and production monitoring.
• Improve instruction following, tool-calling reliability, latency, and cost across the LLM and speech stack.
• Help design and build the next-generation voice agent platform, selecting models and architecture according to quality, latency, and cost.
• Partner with clinical, product, and customer teams to turn scheduling, refills, billing, and post-discharge check-ins into reliable agent behavior.
• Review real conversations and failure cases, then address them through prompt, tool, model, or product changes.
• Build internal tools to observe, monitor, and analyze agent behavior at scale and identify failure modes and patterns.
• Track developments in models and tooling and bring useful capabilities into production.

Benefits

• Meaningful equity.
• Comprehensive health insurance.
• Dental insurance.
• Vision insurance.
• 401(k) plan.
• Learning budget, conferences, and additional benefits are listed as possible benefits in the posting.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed