Enterprise Systems Architect, AI

OpenAI • San Francisco, CA

1d • Hybrid

About The Position

The Enterprise Platform Technology team builds and operates the platforms and integrations that run the company’s core business workflows across Finance, People, Procurement, Legal, and GTM. We deliver secure, scalable system connectivity and AI-native experiences that reduce manual work, strengthen controls, and improve operational reliability across the enterprise stack.
As an MCP Engineer / Enterprise Architect (Agentic Integrations & Enterprise Platforms), you will design and build Model Context Protocol (MCP) servers and integration primitives while shaping the technical architecture for enterprise platforms and AI-enabled workflows. This is an individual contributor role with architectural leadership: you will set standards and reference patterns, lead design reviews, and ship production-grade connectors and guardrails.
You will work hands-on across enterprise systems like Oracle, Workday, Salesforce, Anaplan and Jira, and our own internal systems, ensuring integrations are secure, observable, and built to scale.
We’re looking for people who can turn messy real-world requirements into clean interfaces, think deeply about identity and data boundaries, and balance speed with durability.
This role is based in San Francisco, CA. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees.

Requirements

• 10+ years of experience in enterprise systems architecture, business systems engineering, or IT strategy
• Deep understanding of SaaS application ecosystems (Salesforce, Oracle Fusion, Workday, Ashby, NetSuite, etc) and their APIs/integration frameworks
• Have built production integrations or platform services and you naturally think about security, failure modes, and operational ownership.
• Are strong in API/interface design and modern identity patterns (OAuth/OIDC, service-to-service auth), and can clearly explain tradeoffs across usability, performance, and controls.
• Can lead technically without managing a team: you drive alignment through crisp architecture decisions, high-quality reviews, and shipping reference implementations that other engineers adopt.

Responsibilities

• Build and operate MCP servers/connectors that securely connect LLM-powered workflows to enterprise systems (Oracle, Workday, Salesforce, Anaplan, etc.), including authentication/authorization, auditing, and safe data access patterns.
• Define architecture standards and reusable integration primitives: API/tool schemas, permissioning models, policy enforcement, rate limiting, caching, and guardrails that prevent accidental data exposure and ensure least-privilege access.
• Drive production readiness and reliability: observability (metrics/logs/traces), idempotency/retry patterns, incident-ready runbooks, and pragmatic non-prod→prod rollout paths with measurable risk controls and adoption metrics.
• Adopt OpenAI technologies (Codex) to co-create MCPs with platforms, working with our internal Enterprise Platform team to create MCP actions.
• Assist with other development efforts as needed.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed