Senior Software Engineer, Content Agent

3 Days Old

We're hiring a senior engineer for Content Agent – Sanity's operations layer for structured content. It's the system that turns content work (bulk edits, audits, translation, publishing) into things an agent can actually run. It lives in Dashboard, Studio, Slack, and behind a headless API. If you've spent time on AI systems that have to hold up for real users, not just in a demo, read on. At Sanity, we build an AI-powered content operating system that lets teams model, create, and automate content the way their business actually runs. SKIMS, Figma, Riot Games, Anthropic, COMPLEX, Nordstrom, and Morningbrew run their content operations on it. Content Agent is the part of the product that understands structured content – schemas, references, field types, validation rules – and can be trusted to operate on it correctly. You'd be doing full-stack product work in TypeScript and React: MCP tools and integrations, agent orchestration, system prompts, evals to make the whole thing more reliable. Engineers on this team own their domain and work closely with product on what gets built next. Responsibilities
Deliver full‑stack product work: design and build React interfaces in Dashboards, APIs, and backend services. Develop MCP tools and integrations that extend what the agent can do. Implement agent loops – the orchestration logic that decides what the agent does, in what order, and when to bring a human in. Create and maintain system prompts as engineering artifacts. Run evaluations and experiments to measure and improve reliability in real usage. Utilize GROQ, Sanity's content query language, to give the agent a deep understanding of structured content. Shape the evolution of Content Agent with product and design, balancing innovation and practical constraints.
Qualifications
Strong proficiency in TypeScript and React, comfortable across the stack (frontend, APIs, backend). Experience shipping LLM‑based systems in production. System‑thinking mindset: analyse user intent, edge cases, failure modes, and architecture decisions for new agent capabilities. Strong written communication for crafting clear agent instructions and system prompts. Comfortable with probabilistic systems and data‑driven experiments; ability to read statistical results and iterate on aggregates. Real experience with or strong curiosity about MCP, tool‑use patterns, and agent architectures. High regard for craft in code, writing, and product quality. Non‑traditional background experience (e.g., writing, interaction design, liberal arts) is encouraged.
Location: London, UK or Oslo, Norway (in‑office 2–3 days/week) Sanity.io is an organization that reflects the globally diverse audience that our product serves. We believe that a diversity of perspectives, ideas, and cultures leads to better products and services. We are committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, marital status, disability, or gender identity. #J-18808-Ljbffr
Location:
Greater London
Job Type:
FullTime

We found some similar jobs based on your search