Healthcare Forward Deployed Engineer — Prior Authorization (Medical PA, Rx PA, UiPath, Claude-First)

Remote/Exton, PA

**
About Genzeon Platform**

sGenzeon 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. We are the only vendor running production agentic AI inside CMS Medicare via the WISeR Innovation Model — live in New Jersey since January 2026, processing 12,609 prior-authorization cases in Q1 2026 at 100% three-day TAT compliance, with zero auto-denials by architectural design

.Our patent portfolio (12 patents under USPTO Customer #226167) protects the multi-agent architecture, the no-auto-deny clinician-in-the-loop guarantee, and the Knowledge Containment Architecture that lets sovereign deployments keep weights, knowledge, and decisions inside the customer perimeter. We are headquartered in Exton, Pennsylvania, with US and India delivery

.
The Healthcare FDE practi

ceForward 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 rea

l.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 engagemen

t.
The r

oleYou will build the prior-authorization decision agents and the workflow automation around them — for medical PA (the CMS-0057-F surface, Da Vinci CRD/DTR/PAS, payer medical policy) and for pharmacy benefit PA (the CMS-0062-P proposed-rule surface, NCPDP SCRIPT ePA, formulary criteria). HIP One is the platform you'll be working inside, alongside the team that runs it in CMS Medicare tod

ay.This is not a position where you build a prototype and hand it to a delivery team. You build, integrate with the customer's existing payer or provider stack, deploy to production, watch the first month of real cases, and tune until the outcomes land. WISeR (12,609 PA cases, 100% CMS three-day TAT, <3 minute median latency, zero auto-denials, 35+ AI agents in Q1 2026) is the reference deployment — what we built there is what you'll be extendi

ng.
What you will

ownMedical PA agents. Reasoning agents that evaluate medical-necessity criteria against patient documentation — NCD/LCD criteria for Medicare, InterQual/MCG-equivalent criteria for commercial, per-payer policy logic for plan-specific rules. Per-criterion citation chains, not vibes-based decision
ing.Pharmacy benefit PA agents. Drug PA covered under the pharmacy benefit. NCPDP SCRIPT ePA standard, formulary-aware criteria evaluation, F&B file handling, drug-specific denial reason codes. Dual-channel (NCPDP + FHIR Da Vinci) per the architecture CMS-0062-P is driving tow
ard.UiPath automation surface. Many payer and provider workflows still live in legacy portals, fax queues, and EHR-side screens. UiPath is one of the surfaces we deploy automation against. You will design, build, and maintain UiPath workflows that bridge between the agent-driven decisioning and the customer's existing operational tool
ing.Customer-facing engineering. PA workflows live inside payer organizations and inside large provider systems. You will sit with their utilization-management nurses, their pharmacy ops teams, their clinical reviewers — and build agents that actually fit the workflow, not the architecture diag
ram.Patent-grade specification work. Genzeon Platforms files patents on the architectures we build. ADRs you author may become claim language. We will train you on this — but you have to be willing to write with that level of c

are.
What we need you to

bringStrong production-grade Python (or TypeScript), plus comfort with at least one strongly-typed language. Code-quality discipline matters more than language ch
oice.Healthcare PA domain literacy — or the appetite to acquire it fast. If you've worked on PA workflows in any capacity (payer, provider, vendor, RCM), say so. If you haven't but you can read regulatory text without flinching, that works
too.Working knowledge of HL7 FHIR R4 and the Da Vinci PA stack (CRD, DTR, PAS). If you've implemented or integrated against any of these, that's a plus. If not, you need to be willing to learn fast — the Healthcare Brain Academy Builders Track Step 2 covers
this.NCPDP SCRIPT ePA familiarity. Or pharmacy-benefit workflow experience generally — pharmacy ops, PBM integration, formulary management, F&B files. You'll work alongside teammates with deep depth here, but you should at minimum recognize what these acronyms
mean.UiPath experience. RPA design and build. Studio, Orchestrator, Apps. Comfort connecting UiPath to API-driven agentic services. Not the only automation surface we use, but a core
one.Claude as coding partner — fluently. Spec-first prompting, agent-driven refactors, code-review-by-Claude as muscle memory, test generation, ADR drafting. We expect to see Claude in your day-to-day, not as a
toy.Customer-facing maturity. You can sit in a room with a payer's CMO, the chief pharmacy officer, and a utilization-management nurse, and lead a productive conversation about how an agent will fit their workflow without losing any of
them.5+ years of production engineering experience. Healthcare and / or regulated systems is preferred. Recent grads with exceptional regulated-systems or healthcare side-project depth will be consid

ered.
Nice-to

-havesPrior CMS-0057-F or CMS-0062-P implementation work (payer-side or vendor
-side)Production deployment experience on Microsoft Azure (we deploy heavily here) or Azure Government / AWS Go
vCloudExposure to InterQual or MCG-equivalent criteria sets, or NCD/LCD policy aut
horingFHIR PAS Bundle construction or X12 278 packet construction in prod
uctionPatent author / inventor credit (we'll teach this, but if you've done it, s
ay so)Anthropic Claude API or Claude Code at production
scaleExperience with vLLM, Ollama, llama.cpp, or quantized open-weight inference in prod

uction
Common expectations for every Healthc

are FDEHealthcare Brain Academy — Builders Track. Every Healthcare FDE works through Steps 1–4 of the Builders Track before customer engagement. CPT / ICD-10 / HCPCS literacy, regulatory framework, production discipline, and clinical validation are the floor — not optional r
eading.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 doesn't work in production, the work isn't 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 explainability, 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 o
f code.Customer-facing communication. FDEs talk directly to customer engineering, clinical, compliance, and business stakeholders. We expect engineers who can write a defensible compliance memo as comfortably as they write a service h

andler.