OpenAI
AI Deployment Engineer, Plugins
San Francisco · Contract
Sponsorship not specifiedDetected 7 days ago
Distributed SystemsBackend DevelopmentAPI DevelopmentOAuthLLMsResearchLeadershipCommunication
About the role
- The best person for this role moves fluidly between code, product judgment, project leadership, and clear communication with engineers and executives.
- This role is based in our San Francisco office.
- We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees.
Responsibilities
- Own the technical partner journey for priority B2B plugins-from pitch and readiness assessment through architecture, build, evaluation, submission, launch, and ongoing maintenance.
- Identify strong plugin use cases, define crisp user journeys and expected behaviors, and help partners focus on workflows where ChatGPT or Codex can create meaningful user value.
- Write production and sample code, build prototypes and reference implementations, and create the technical guidance, evals, launch checklists, and debugging tools that move partners from concept to production.
- Debug API contracts, OAuth/login, tool invocation, latency, retries, rate limits, observability, data model, and user-experience issues across partner and OpenAI systems.
- Review partner architectures and implementation plans for API design, scopes and permissions, data handling, safety, privacy, reliability, and long-term maintainability.
- Contribute targeted fixes and improvements to ChatGPT, Codex, and the plugins platform, including APIs, SDKs, docs, examples, internal tooling, partner debugging workflows, and launch guardrails.
- Work with product, engineering, design, partnerships, legal, policy, support, and go-to-market teams to make partner launches smooth and repeatable.
- Can make ambiguous partner ideas concrete through runnable prototypes, API contracts, technical specs, and pragmatic implementation guidance.
Nice to have
- Experience with OAuth/login flows, API design, webhooks, schemas, rate limits, observability, SDKs, and production launch operations.
- Familiarity with AI products, LLM APIs, tool calling, MCP, ChatGPT or Codex surfaces, developer platforms, or marketplace ecosystems.
- Comfortable making targeted changes across backend services, frontend surfaces, SDKs, docs, internal tools, or monorepo codebases when needed.
- We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products.
- For additional information, please see OpenAI's Affirmative Action and Equal Employment Opportunity Policy Statement https://cdn.openai.com/policies/eeo-policy-statement.pdf.
- return all computer hardware in your possession (including the data contained therein) upon termination of employment or end of assignment
- In addition, job duties require access to secure and protected information technology systems and related data security obligations.
- To notify OpenAI that you believe this job posting is non-compliant, please submit a report through this form https://form.asana.com/?d=57018692298241&k=5MqR40fZd7jlxVUh5J-UeA.
Company info
- The Ecosystem AI Deployment Engineering (ADE) team supports strategic partners as they build high-quality technical integrations into ChatGPT and Codex.
- Our goal is to create products users depend on, drive adoption and retention, and build an ecosystem where partners win when OpenAI wins.
This listing is sourced directly from OpenAI's careers page and normalized into a canonical job model.