Senior AI Engineer, Tools & Agents
About The Position
TwelveLabs is building the intelligence layer for video data, enabling machines to understand video content across sight, sound, and motion. The company has raised over $210 million from prominent investors and partners. Headquartered in San Francisco with offices in Seoul, New York, and London, TwelveLabs values diversity and seeks individuals driven by challenging problems. This role focuses on the integration layer that makes TwelveLabs' video AI accessible to external developers and AI agents. The engineer will own the "Jockey" multimodal agent, which is built on a knowledge store, retrieval primitives, and an agent layer for planning and reasoning. The core responsibility is to design and operate the surfaces that allow AI agents and developers to connect to these capabilities, ensuring trustworthiness at an enterprise scale. This includes owning the MCP server end-to-end, handling capability discovery, invocation, tool interfaces, failure modes, and the evolution of the surface. The role also involves building the supporting infrastructure for authentication, metering, and rate limiting to ensure enterprise trust.
Requirements
- Shipped production agentic or LLM-powered systems with real users and real failure modes.
- Understanding of how retrieval, reasoning, and agent orchestration fit together as a system.
- Experience owning a developer-facing or external API end-to-end, including decisions about contracts and versioning.
- Experience building authentication and authorization in production (OAuth, OIDC, RBAC, or multi-tenant isolation) as a primary owner.
- Experience considering enterprise-readiness for platforms.
- Versatility across the full platform surface, not just specialization.
- Experience operating in a fast-moving environment (startup, hypergrowth, or AI-first team) with ambiguity and minimal process support.
Nice To Haves
- Experience with MCP, A2A protocols, or the broader agent ecosystem.
- Hypergrowth pedigree from a technically excellent startup.
Responsibilities
- Own the agent-facing integration surface, including TwelveLabs' MCP server and agent-to-agent interfaces.
- Design how AI agents discover, connect to, and build on Jockey's retrieval and reasoning capabilities.
- Own the auth and access substrate, including OAuth, RBAC, and multi-tenant isolation for enterprise customers.
- Build the enterprise-readiness layer, including per-API-key usage tracking, rate limiting, and reliability work.
- Partner with the research team to translate frontier video and image understanding capabilities into durable product surfaces.
Benefits
- An open and inclusive culture and work environment.
- Work closely with a collaborative, mission-driven team on cutting-edge AI technology.
- Full health, dental, and vision benefits.
- Extremely flexible PTO and parental leave policy.
- Office closed the week of Christmas and New Years.
- VISA support where applicable.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
