AI Engineer (Agentic AI)

Healthcare Forward Deployed Engineer: AI Engineer(AI/ML Agent Engineering)

Remote

Full Time

Aether One™ agent graphs · RAG over clinical ontologies · Evaluation and guardrails · Claude-First

Build the agents that make clinical decisions in production. Multi-agent graphs on the Aether One™ substrate, retrieval over regulatory and clinical knowledge, per-criterion citation chains, and the evaluation harness that decides whether any of it ships. Live Medicare volume from your first quarter.

About Genzeon Platforms

Genzeon Platforms is building the Healthcare Brain: agentic AI decision infrastructure for healthcare. Three production platforms (HIP One, PES One, CPS One) run on the Aether One™ agentic substrate, serving 50+ enterprise platform clients across payers, providers, and government.

We are one of six commercially available platforms operating inside CMS Medicare through the WISeR Innovation Model, live in New Jersey since January 2026, and the only participant available across every deployment environment (sovereign, government cloud, commercial cloud, on premises) and every consumption model.

The Healthcare FDE practice

Forward Deployed Engineer is a different shape of role than traditional consulting or platform engineering. An FDE owns the outcome the customer hired us for, not the ticket, not the sprint, not the surface area. Forward Deployed means embedded with the customer, in their codebase, in their workflow, in their decision-making, building until the outcome is real.

We deliver in pods: four to five people, typically two or three FDEs alongside one or two Domain Operators who bring lived clinical, payer, and regulatory fluency. The pod owns a measurable outcome on a four to twelve week clock. You will not hand a prototype to a delivery team, because there is no delivery team.

Healthcare FDE adds the domain. We hire engineers who can read a Local Coverage Determination, understand why a CARC 50 / RARC N386 combination matters, and tell the difference between Medicare Advantage and Medicare FFS without being told. The Healthcare Brain Academy, our published Builders and Client Engagement tracks, defines the minimum knowledge bar. Every FDE works through it before customer engagement.

Velocity Standard

Our engineering culture is the Velocity Standard: domain leverage, Claude-First by default, ship to production weekly, own the outcome. Claude is the coding partner across the entire SDLC, including agent scaffolding, eval-set generation, regulatory-text decomposition, prompt and context iteration, code review, and customer documentation.

More than 30 of our engineers hold Claude Architect Foundational certification and 50+ work in Claude Code daily. The Healthcare Brain running in CMS WISeR was built Claude-First.

What you will own

•Agent graph design on Aether One™. Multi-agent decomposition of clinical decision workflows. State machines, not conversation loops. Tool design, control flow, retry and fallback semantics, partial-failure behavior, and typed contracts between agents. LangGraph is our common shape; the reasoning behind the graph matters more than the framework.

•Retrieval over clinical and regulatory knowledge. RAG across NCDs, LCDs, payer medical policy, formulary criteria, and coding references (CPT, ICD-10, HCPCS, LOINC, RxNorm, SNOMED). Chunking and indexing strategies that preserve citation granularity, because a decision has to point at the exact criterion it turned on. Hybrid retrieval, reranking, and retrieval evaluated separately from generation.

•Per-criterion citation chains. Every determination traces to the specific policy language that produced it. This is an architectural requirement, not a feature. If the chain breaks, the decision is not defensible, and if it is not defensible we do not ship it.

•Evaluation harness and quality gates. Gold-standard case sets built with clinician adjudication. Regression suites wired into CI. Agreement metrics against human reviewers, drift monitoring on live traffic, and a clear-eyed view of where LLM-as-judge is useful and where it quietly lies. Eval pass rate is a number we publish, not a number we claim.

•Deterministic guardrails and the no-auto-deny invariant. Zero auto-denials is enforced in architecture, not in a prompt and not in a config flag. You build the routing, the human-in-the-loop gates on adverse outcomes, and the assertions that fail the build when an invariant is violated.

•Model routing and the containment boundary. Frontier reasoning is rented and swap-capable; the knowledge overlay is owned and stays customer-side. You work across that boundary: Claude and other frontier models where they fit, open-weight local substrates where sovereign or air-gapped deployment demands it, and the routing logic that decides which handles what.

•Read paths into the Healthcare Brain. Knowledge packs, MCP servers, and Claude Skills are how agents and customer teams consume governed context instead of prompts and hope. You build and maintain those surfaces for the workflows you own.

•Customer-facing agent engineering. You will sit with utilization-management nurses, pharmacy operations teams, medical directors, and the customer's own engineers. You will watch your agent handle their real cases, take the feedback in the room, and tune. You stay embedded through the first 90 days of production.

What we need you to bring

•Production agentic systems, not demos. You have shipped multi-step agents that ran against real traffic and real failure modes. LangGraph, LangChain, DSPy, Temporal-backed orchestration, or something you built yourself. What we look for is whether you can explain why the graph is shaped the way it is and what happens when step four returns garbage.

•Strong production Python. FastAPI, async patterns, PostgreSQL, pgvector or ChromaDB, clean typed interfaces, real test discipline. Comfort with at least one strongly-typed language is a plus. Code quality matters more than framework familiarity.

•Retrieval engineering depth. You have built and debugged RAG in production over messy, structured, and semi-structured source material. You know why naive chunking destroys citation traceability, you have measured retrieval quality independently of answer quality, and you have opinions about reranking that came from data.

•Evaluation as a first-class discipline. You have built eval sets rather than eyeballing outputs. Offline and online evaluation, human agreement measurement, regression gating, and honest calibration of where automated judges break down. If you have run evals against expert-labeled ground truth, lead with that.

•Prompt and context engineering at production scale. Structured output, tool and function-call design, context budgeting, failure containment. Treated as engineering with tests and versions, not as copywriting.

•Healthcare regulatory literacy. CPT, ICD-10, and HCPCS fluency. NCD and LCD structure. Medical necessity criteria and how InterQual or MCG-equivalent criteria sets are actually applied. CMS-0057-F at minimum. PHI handling discipline that is instinct rather than a checklist. This is a hard requirement for this seat, not a preference.

•Claude as coding partner, fluently. Spec-first prompting, agent-driven refactors, code review by Claude as muscle memory, Claude-assisted eval and test generation, ADR drafting. We expect Claude visible in your day-to-day, not as a toy.

•Customer-facing maturity. You can sit with a chief medical officer, a UM nurse, and a payer's head of engineering in the same room and lead a productive conversation about how an agent will fit their workflow without losing any of them.

•5+ years of production engineering experience, with at least 2 building LLM or ML systems that ran in production. Healthcare or regulated-systems depth strongly preferred. Exceptional candidates slightly under the bar with unusually strong production agent work will be considered.

Nice-to-haves

• Fine-tuning, LoRA, distillation, or preference optimization on clinical or regulatory corpora

• Open-weight inference in production: vLLM, Ollama, llama.cpp, quantization, and the tradeoffs that come with each

• Vision-language pipelines for chart mining, medical record digitization, or document extraction

• MCP server authoring, or Claude Skills built for a production workflow

• Sovereign, air-gapped, FedRAMP-aligned, or Azure Government / AWS GovCloud deployment experience

• FHIR R4, Da Vinci CRD/DTR/PAS, X12 278, or NCPDP SCRIPT familiarity

• Published open-source or research contribution in agents, retrieval, or evaluation

• Patent author or inventor credit on AI or decision-system architecture

• Anthropic Claude API or Claude Code at production scale

Common expectations for every Healthcare FDE

• Healthcare Brain Academy, Builders Track. Every Healthcare FDE works through Steps 1 to 4 of the Builders Track before customer engagement. CPT / ICD-10 / HCPCS literacy, regulatory framework, production discipline, and clinical validation are the floor, not optional reading.

• Claude-First engineering. Spec-driven development. ADRs within 24 hours of design decisions. Invariant assertions in every ADR. Claude is the coding partner across the SDLC; we expect comfort and discipline using it, not aversion to it.

• Ownership of the outcome. FDE means you own the customer outcome end-to-end, not the JIRA ticket. If the workflow does not work in production, the work is not done, regardless of how clean the code looks.

• Production-grade discipline. Healthcare AI in production has different gates than experimental ML. Per-decision citation chains, audit-grade explain ability, cryptographic decision ledgers, and human-in-the-loop on every adverse outcome are not features we add later. They are architectural requirements from line one of code.