Want to know if this job is worth applying to?
Palo Alto, California, United States
Onsite
SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where we are not. Today, SpaceX is actively developing the technologies to make this possible, with the ultimate goal of making life multiplanetary and expanding consciousness to the stars.
SpaceXSI is building Super Intelligence to help humanity understand the universe. Our teams are building the full Super Intelligence stack: from our Colossus supercomputers, to Grok models, to our suite of applications, including Grok Bot, Grok Build, Grok Imagine, Grok Voice, and X. We're creating a powerful flywheel where more compute trains better models, better models power more useful products, and what we learn from people using those products shapes what we build next.
As a Product Engineer on the Grok Connectors team at SpaceXAI, you'll build the integrations that let Grok, Cursor and Grok Bot do real work inside the tools people use every day: Gmail, Outlook, Google Calendar and Drive, Microsoft Teams, OneDrive and SharePoint, GitHub, Slack, finance accounts, and a fast-growing marketplace of third-party MCP plugins. You'll architect, implement, and deploy features end to end, from OAuth sign-in and token handling, to tool schemas and reliability across hundreds of millions of tool calls, to the cards and approval flows users see on web, desktop, and mobile. You'll work directly with enterprise customers and partners to ship connectors that large organizations can trust.
You have an entrepreneurial spirit and love creating outsized business impact.
You want AI agents to be genuinely useful, by connecting them to real data and real actions safely.
You have deep, practical knowledge of OAuth 2.0 and OIDC and of large provider APIs like Google Workspace and Microsoft Graph, or you're excited to become the expert.
You care about reliability: concurrency, retries, rate limits, and observability. You fix root causes, not symptoms.
You let data decide what to work on. You size user impact from logs and metrics, and you measure error rates before and after every fix.
You're strong in TypeScript and comfortable shipping across backend services and client UI in a large codebase.
You enjoy working with customers, partners, QA, and support, and can answer a security review question as clearly as you can fix a bug.
Bonus: experience with the MCP protocol, Rust, Kubernetes and multi-cloud deployments, enterprise security and compliance (ZDR, audit logs, Conditional Access), or building LLM agents for automation.
Building an automated triage system that pulls user reports from feedback channels, groups them by root cause with user-impact estimates, files issues, and starts a first-pass coding agent on each fix
Redesigning OAuth token refresh so concurrent requests never burn a single-use refresh token and mark a working connector as disconnected
Cutting hundreds of thousands of daily tool-call errors by generating tool definitions from vendors' published API specs, fixing argument mapping, and adding batch tools
Shipping Gmail and Outlook draft, reply, and attachment flows, with approval cards so an agent never sends an email without the user's sign-off
Launching new partner connectors, from debugging a partner's OAuth metadata to rollout and adoption metrics
Making connectors work for enterprise and single-tenant deployments: custom certificate authorities, Entra Conditional Access, admin controls, and compliance reviews with large financial institutions
If there appears to be a fit, we'll reach out to schedule 2-3 short technicals. After, we'll schedule an onsite in our office, where you'll work on a small project, discuss ideas, and meet the team.
