Skip to main content
Back to jobs

Principal Engineer, AI Platform

External
Epic Games logoEpic Games · Cary, NC
Full-timeOn-site1mo ago30+ days old, may be filled
Kubernetes
Cover LetterConnect

Prepare for this interview

Elite

AI-generated questions, company research, and talking points tailored to this role


Responsibilities

  • Geppetto - multi-tenant platform for team AI agents that live and collaborate in Slack channels
  • EMA (Epic Managed Agents) - compute and workspace infrastructure for headless agent harness runs at scale
  • Hodor - MCP OAuth gateway, plugin runtime, and governance layer for AI tool orchestration (1,500+ MAU, 700K+ tool executions)
  • Multipass - agent identity, credential vault, and authorization for non-human workloads
  • Vektor - org-wide memory plane with knowledge graph, deductive reasoning, and hierarchical summarization
  • Roost - cryptographically signed software distribution and the Claude Code plugin marketplace
  • This is foundational work that will define how AI is used inside Epic for the next decade. The scale is real, the problems are hard, and the team is small enough that every engineer makes a decisive architectural impact.
  • In this role, you will
  • Platform Architecture & Technical Leadership:
  • Own the end-to-end technical architecture across Geppetto, EMA, Hodor, Multipass, Vektor, and Roost - ensuring each platform is coherent with the others and that the integration seams are well-defined
  • Drive architectural decisions for agent identity and workload authorization (SPIFFE/SPIRE, OIDC, token exchange, policy planes), translating security requirements into implementable designs
  • Establish the patterns for how AI agents authenticate, receive credentials, execute tools, and are audited - and hold the bar for correctness across the stack
  • Lead design reviews for new capabilities, evaluate build vs. buy decisions, and surface technical risk before it becomes production risk
  • Distributed Systems & Infrastructure:
  • Design and implement the Cluster API and provider abstractions for EMA - the layer that orchestrators depend on to launch, drive, and recover headless agent runs across Kubernetes, EC2, and other compute backends
  • Evolve Hodor's plugin runtime (WASM, gRPC sidecar, subprocess multiplexer) and its gateway security posture as external tool surface area grows
  • Architect Vektor's knowledge graph, vector search

Additional Information

WHAT MAKES US EPIC? At the core of Epic's success are talented, passionate people. Epic prides itself on creating a collaborative, welcoming, and creative environment. Whether it's building award-winning games or crafting engine technology that enables others to make visually stunning interactive experiences, we're always innovating. Being Epic means being a part of a team that continually strives to do right by our community and users. We're constantly innovating to raise the bar of engine and game development. ONLINE INFRASTRUCTURE What We Do We enable Epic's online services teams to build, deploy, and manage services that are used by more than half a billion players around the world. Our mission is to provide world class tools and platforms to improve the experience of our developers and make it easier, faster, and safer to build, operate, and scale their applications. We operate at massive scale as one of the largest cloud computing users in the world.


Your Match

How well this role fits your profile.

Company Intel

What employees say

Worked at Epic Games? Share your experience

Interested in this role?

Apply on the company's website.

Cover LetterConnect