Forward Deployed Engineer

Role overview

Zyter is hiring a Forward Deployed Engineer (FDE) to build and deploy an agentic AI platform for a large integrated healthcare system.

In this role, you will work directly with clinicians, referral coordinators, and process improvement teams to turn their workflows into functional AI tools, from initial prototypes through shadow-mode operation.

Key responsibilities

Build and deploy the platform

• Configure bounded AI agents that break down approved tasks, call approved tools and data services, draft outputs, create work queues, and escalate to people.
• Build retrieval and source-citation features that show the exact record elements, dates, and excerpts behind each AI output, including uncertainty and missing information.
• Build ingestion pipelines for structured, semi-structured, and unstructured healthcare data, including clinical notes, reports, policies, and requirements documents, with data lineage, quality checks, and retention controls.
• Work with business and clinical users to gather feedback and iterate rapidly.
• Troubleshoot issues across configuration, APIs, data, AI behavior, and workflow orchestration.
• Maintain and prioritize the configuration and FDE backlog.
• Apply clinical and operational natural language processing (NLP) to extract diagnoses, results, orders, appointments, consult details, and referral prerequisites.
• Build risk and criticality classifiers with thresholds the client can adjust by specialty, facility, and policy.
• Build role-based review queues and case views for clinicians, nurses, referral coordinators, and program managers.

Work directly with client teams

• Conduct discovery sessions with client subject matter experts at least every two weeks and translate findings into user stories and working features.
• Model referral pathways, prerequisites, and status transitions with referral coordination teams.
• Support service blueprinting by synthesizing stakeholder interviews and documents into blueprints, data maps, and requirements.
• Deliver demonstrations during sprint reviews and make adjustments based on user feedback.

Deliver in a regulated environment

• Deliver code in Scaled Agile Framework (SAFe) sprints, with 26 sprints per year and weekly release windows on an AWS cloud platform.
• Write automated unit, integration, and regression tests and use continuous integration and continuous delivery (CI/CD) pipelines.
• Track requirements, code, tests, and risks in Atlassian tools, including Jira and Confluence, to ensure requirements are traceable to tests.
• Measure output quality, reviewer agreement, false positives and negatives, and model drift, and contribute to model cards and evaluation reports.
• Provide Tier III production support and develop technical design and operational documentation for transition.

Required qualifications

• Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent experience.
• 5+ years of software engineering experience, including 3+ years building and deploying large language model (LLM) or AI applications to production.
• Hands-on experience with agentic workflows and retrieval-augmented generation (RAG), including prompt design, tool calling, vector search, and output evaluation.
• Strong Python skills, along with experience building REST APIs and data pipelines.
• Experience deploying on AWS with CI/CD, containers, and automated testing.
• Experience working directly with business or clinical users to gather requirements and iterate on working software.
• Strong written and verbal communication skills, including the ability to deliver demonstrations to non-technical stakeholders.
• U.S. work authorization and residence in the United States.

Preferred qualifications

• Experience with healthcare data and standards, including HL7 FHIR, clinical notes, laboratory and imaging results, and EHR workflows such as Epic or Oracle Health.
• Clinical NLP experience, including entity extraction from clinical text.
• Experience with SAFe or Scrum methodologies and Atlassian tools.
• Familiarity with model evaluation and AI governance, including model cards, bias testing, drift monitoring, and human-in-the-loop review.
• Front-end development experience with React or similar frameworks and familiarity with the U.S. Web Design System.