Support Systems Architect

OpenAI•San Francisco, CA

11h•Hybrid

About The Position

We are seeking a systems‑minded builder who will design, prototype, implement, and iterate on the tooling, data flows, and processes that allows the User Operations team to redefine a modern support organization. Think: automated launch checklists, content and knowledge pipelines, incident detection and evaluators, and other processes that power a User Operations team operating at an unprecedented scale. You’d be building resilient systems, not better slide decks. We’re looking for people who thrive at the intersection of project management, systems building, data science/data engineering/software engineering, team enablement, and customer advocacy – and enjoy working cross-functionally in a fast-paced, evolving environment. This role is based in San Francisco, California. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees.

Requirements

Have 8+ years of experience in building tools for internal teams, especially within a customer support environment.
Have shipped or maintained tools and automations (dashboards, ETL pipelines, low-code apps) that eliminated manual work and scaled beyond a single team.
Treat ChatGPT & LLMs as default co-developers, rapidly turning natural-language ideas into working code or queries.
Deeply enjoy working cross-functionally and are skilled at building relationships with Product, Engineering, and Operations teams.
Are passionate about customer advocacy and have experience translating customer feedback into strategic product insights.
Possess a strong bias for automation and a distaste for doing low-complexity to otherwise repetitive work consistently.
Thrive in a fast-moving, ambiguous environment where priorities will shift quickly and iterating on your systems will be required.

Responsibilities

Build “Day-1 enabled” workflows; role-tailored playbooks, content auto-diffs from source docs, and other workflows that have been taken for granted in typical Support organizations.
Continuously automate repetitive touchpoints with scripts, agents, and LLM-powered flows; implement governance, observability, evaluation gates, and safe rollback.
Codify detection (windowing, dedupe, thresholds), on-call handoffs, and post-incident learning loops that protect customer experience and SLAs.
Prototype and learn quickly—leveraging ChatGPT, Jupyter notebooks, Retool, and other tools—to prove value before hardening with Engineering.
Stand up data pipelines that capture sentiment, ticket trends, and BPO insights, routing actionable signals back to Product within hours—not weeks.
Identify risks and challenges during tooling rollouts, proposing solutions that safeguard customer experience and service levels.
Continuously automate, replacing every repetitive touchpoint with scripts, agents, or LLM-powered flows.