Principal Engineer, Agent Platform
Gap Inc. · SF - 2 Folsom; Dallas-Coppell; Vari
Apply on Gap Inc.’s siteAsk about this jobApply opens the employer’s own application. Nothing is sent from here.
What the posting says
Each fact was read from this posting and checked:Statedin the posting, quotedConflictsposted two ways, both shownNot mentionedwe looked; it is not there
- Employment typeStated
- Full time
Not mentioned in this posting
We read the whole posting. These are not in it. Not a no: ask the recruiter, in your own words.
- PayNot mentioned
- The posting does not say
- Work arrangementNot mentioned
- The posting does not say
- ShiftNot mentioned
- The posting does not say
- ExperienceNot mentioned
- The posting does not say
- EducationNot mentioned
- The posting does not say
- Visa sponsorshipNot mentioned
- The posting does not say
Requirements, each with its sentence from the posting
These are the employer’s words. The index does not judge whether you meet them.
- No requirement has been itemized for this posting yet. The employer’s words are in the full posting below.
Read the full posting as the employer wrote it
About the Role
We are building the enterprise AI agent platform that teams across the company will use to create, deploy, govern, and operate AI-powered solutions at scale. As a Principal Engineer, you will help define the technical foundation for agent development across the organization, building the services, frameworks, and guardrails that make AI agents secure, reliable, observable, and easy to adopt.This is a hands-on engineering role focused on architecture, software design, and platform development. You will work across AI, distributed systems, cloud infrastructure, security, and governance to deliver a platform that enables product and engineering teams to move quickly while meeting enterprise standards for security, compliance, and operational excellence.
What You'll Do
- Design and build core platform services that enable enterprise AI agent development and operations
- Define the architecture, engineering patterns, and technical standards for the AI agent platform
- Develop and maintain a centralized model gateway for routing, governance, resiliency, and cost management
- Build agent runtime capabilities that support long-running workflows, orchestration, and human-in-the-loop processes
- Design secure identity, authorization, and policy enforcement mechanisms for agents and tools
- Establish platform capabilities for context management, memory, retrieval, and data isolation
- Create testing, evaluation, and release frameworks that ensure agent quality, safety, and performance
- Implement observability, auditability, and operational tooling for monitoring and troubleshooting agent behavior
- Partner with Security, Data Governance, and Cloud Infrastructure teams to define platform controls and guardrails
- Mentor engineers, influence technical direction, and raise engineering standards across multiple teams
Who You Are
- Extensive experience building and operating large-scale distributed systems in production
- Strong software engineering background with expert-level Python development skills
- Hands-on experience delivering production LLM, generative AI, or agent-based solutions
- Deep understanding of agent architectures, orchestration patterns, and enterprise AI platforms
- Experienced with retrieval systems, embeddings, vector search, and context management strategies
- Knowledgeable in AI evaluation, testing methodologies, and quality assurance for non-deterministic systems
- Proficient with Google Cloud services including Vertex AI, Gemini, GKE, Cloud Run, BigQuery, and Pub/Sub
- Experienced with cloud security, workload identity, OAuth, policy-as-code, and secure-by-design architectures
- Strong understanding of distributed system reliability patterns, including resiliency, retries, observability, and fault tolerance
- Proven ability to influence technical direction, drive adoption of architectural standards, and lead through expertise rather than authority
The posting text is reproduced as the employer wrote it; the index adds nothing to it.