About the job
As a Principal Engineer on the AI Platform team, you'll own the technical direction of our agent infrastructure stack end to end. You'll set the architecture across the six platforms above, drive alignment between them, and personally solve the hardest distributed systems and security problems that emerge as the stack scales. You'll work across teams to ensure agent identity, tool governance, memory, and execution infrastructure are coherent, secure, and operable — and you'll mentor the engineers who build alongside you. This isn't a coordinator role. You'll write production code, design protocols, make the calls that determine how agents authenticate and what they're allowed to do, and be accountable for the reliability of systems that are actively used by Epic's engineering organization.
Responsibilities
Own the end-to-end technical architecture across Epic's AI Infrastructure Platforms and drive architectural decisions for agent identity and workload authorization.
Design and implement the Cluster API and provider abstractions for EMA, and evolve the AI MCP Gateway plugin runtime.
Architect Epic's knowledge graph, vector search, and memory consolidation pipeline for org-wide scale.
Lead the AI NHI Identity proposal from strategy into staffed execution and hold the standard for credential security across the stack.
Partner with product, ML, and enterprise platform teams, and mentor senior and staff engineers across the team.
Qualifications
Minimum
12+ years of software engineering experience, with at least 4 years at staff or principal scope
Deep expertise in distributed systems: event-driven architectures, durable execution, service mesh, and multi-tenant platform design
Production experience with authentication and authorization infrastructure — OAuth 2.0, OIDC, SPIFFE/SPIRE or equivalent workload identity, token exchange (RFC 8693), and policy engines (OPA, OpenFGA, or comparable)
Strong security engineering fundamentals: credential vaulting, secrets management (OpenBao/Vault), audit trail design, and least-privilege access at scale
Fluency in at least one compiled, systems-capable language (Go preferred, Rust or C++ acceptable); comfort reading and writing Go microservices is essential given the stack
Track record of owning multi-service platform architecture across a full product lifecycle — from design through sustained production operation
Exceptional written communication: design documents and architecture reviews that are clear, precise, and influence without authority
Hands-on experience building LLM-integrated systems: agent orchestration, tool-use frameworks, MCP (Model Context Protocol), or equivalent agent-to-tool middleware
Experience with plugin or extension runtime design — WASM sandboxing, gRPC sidecar patterns, subprocess isolation, or comparable capability security models
Familiarity with knowledge graph systems (Neo4j or comparable), vector databases, and hybrid retrieval (semantic + keyword + graph), as well as experience operating Kubernetes-based platforms: scheduling, workload identity, sidecar injection, and multi-tenancy isolation
Preferred
No preferred qualifications listed.