AI Agent Engineer – Healthcare

Location: Remote, located in the US
Type: Full-time
Department: Engineering
Reports to: Head Of Engineering

Ellipsis Health is creating cutting-edge AI/ML products that solve healthcare staffing issues and administrative burdens using conversational AI and our patented voice biomarker technology in the delivery of better healthcare for everyone. We are headquartered in Silicon Valley and are funded and supported by some of the most preeminent venture capital teams.

We’re seeking a strong and creative AI Agent Engineer with a passion for language and healthcare to help design, implement, and optimize prompts, function tools, knowledge bases, and workflows for our AI-powered healthcare agents. In this role, you’ll work closely with engineering, product, and clinical teams to ensure that the AI has the right information at the right time and that outputs are clinically accurate, context-aware, and delivered with empathy.

You’ll play a central role in shaping how our large language models communicate with patients, providers, and care teams—defining context schemas, retrieval strategies, and production-grade prompts that drive safe, consistent, and patient-centered interactions. The ideal candidate blends engineering skill with a product mindset, thrives on iteration and experimentation, is meticulous in their approach, and has a deep interest in conversation design, natural language interactions, and building reliable AI systems in healthcare.

• Design, write, and maintain production-grade prompts, implement function tools and build workflow graphs for AI agents to support healthcare tasks such as patient outreach, enrollment, symptom screening, and follow-up care.
• Implement and evolve function tools (structured actions, validations, handoffs, and integrations) that agents can invoke during conversations.
• Build and maintain conversation workflows and graphs, including branching logic, guardrails, recovery paths, and escalation flows.
• Design and own context assembly pipelines, including what data, memory, and tool outputs are provided to the model at each step of an interaction.
• Create and curate knowledge base documents (retrieval-ready, model-friendly) and define strategies for grounding agent responses in trusted content.
• Ensure AI outputs adhere to health literacy standards, inclusive language, cultural sensitivity, and regulatory expectations, driven by both prompt design and structured context.
• Evaluate AI behavior end-to-end, identify whether failures are driven by prompting, missing or misleading context, retrieval issues, or model limitations, and iterate accordingly.
• Stay current on LLM capabilities, orchestration patterns, and ethical standards for deploying AI in regulated healthcare environments.

• Experience building or shipping LLM-powered applications in healthcare or other regulated environments, involving both prompt engineering and dynamic context, retrieval, or orchestration.
• Strong written communication skills, with the ability to craft clear prompts and define structured context inputs.
• Ability to reason about LLM system behavior, diagnose failures, and determine whether issues stem from prompts, context, retrieval, or model limitations.

• Experience working in healthcare or other regulated environments, including awareness of HIPAA and PHI handling.
• Familiarity with conversational AI or voice agents, including multi-turn dialogue, latency constraints, and error recovery.
• Experience with knowledge retrieval systems (RAG, embeddings, structured KBs).
• Familiarity with LLM observability or evaluation tools (e.g., Langfuse, prompt eval frameworks).
• Background in digital health, care coordination, or patient-facing systems.
• As a health technology company, we reserve the right to run a background check on any applicant to which we extend an offer and to re-perform any such check at any time during the course of employment. Please know that there is no set policy on rejecting candidates because of certain background check results, and that we look at a candidate as a whole before making any decisions.
  
  We comply with all “ban the box” laws in applicable jurisdictions.

• We offer competitive salary and benefits, including a 401k that matches up to a certain percentage of your salary, health, vision, and dental insurance, and very flexible paid time off. The typical salary range for this role is $150,000 to $180,000 USD. The amount offered will be determined by a variety of factors, including but not necessarily limited to your skills, qualifications, and past experience relative to the role’s requirements.

• If you have a disability or require accommodations during the application or recruitment process, please contact .