• Work on Content Agent, Sanity's operations layer for structured content, which turns content work like bulk edits, audits, translation, and publishing into things an agent can actually run.
• Build the part of the product that understands structured content, including schemas, references, field types, and validation rules, and can be trusted to operate on it correctly.
• Ship across Dashboard, Studio, Slack, and a headless API.
• Do full-stack product work in TypeScript and React, covering MCP tools and integrations, agent orchestration, system prompts, and evals that make the whole thing more reliable.
• Own your domain and work closely with product on what gets built next, with a lot of latitude to shape what Content Agent becomes.
• Work from the London or Oslo office 2-3 days a week.
📋 Job Requirements
• Bring strong TypeScript and React and stay comfortable across the stack, from frontend through APIs to backend, without wanting to be boxed into one layer.
• Have shipped LLM-based systems in production, knowing the hard part is not getting a model to do something once but getting it to do the right thing for every user who shows up.
• Think in systems: given a new agent capability, work through user intent, edge cases, failure modes, and what that means for what the agent knows, what tools it has, and when it escalates.
• Write well and care why one phrasing works where another does not, since an agent's instructions are prose running on a system that reads literally.
• Work comfortably with probabilistic systems, running experiments, designing evals, reading results statistically, and not chasing individual failures when the aggregate trend is what matters.
• Bring real experience with, or real curiosity about, MCP, tool-use patterns, and agent architectures.
• Care about craft in code, in writing, and in the products you ship.
• Be based in London or Oslo.
🌟 Nice-to-have
• Have built MCP tools or integrations.
• Have worked with GROQ or another content query language.
• Have designed eval suites for production LLM systems.
• Come from a non-traditional background such as writing, interaction design, or liberal arts, with real engineering skills built on top.
🎯 Responsibilities
• Do full-stack product work across React interfaces in Dashboards, APIs, and backend services.
• Build MCP tools and integrations that extend what the agent can do.
• Build agent loops: the orchestration logic deciding what the agent does, in what order, and when to bring a human in.
• Write system prompts, treated as real engineering artefacts rather than a note at the top of a file.
• Run evals and experiments to measure and improve reliability in real usage.
• Use GROQ, Sanity's content query language, to give the agent a deep understanding of structured content.
• Shape what Content Agent becomes alongside product and design.
About Sanity
😃 What Sanity offers
• Join a highly skilled, inspiring, and supportive team.
• Work in a positive, flexible, trust-based environment that encourages long-term professional and personal growth.
• Work with a global, multi-culturally diverse group of colleagues and customers.
• Access comprehensive health plans and perks.
• Keep a healthy work-life balance that accommodates individual and family needs.
• Receive a competitive stock options programme and location-based salary.
💖 What makes Sanity unique
Sanity builds an AI-powered content operating system that lets teams model, create, and automate content the way their business actually runs, replacing rigid legacy content management systems. It treats content as data so it can live in a single source of truth while adapting to any channel, and companies including SKIMS, Figma, Riot Games, Anthropic, Nordstrom, and Morning Brew run their content operations on it. The 200+ person company recently raised an $85 million Series C led by GP Bullhound, with backing from ICONIQ Growth, Threshold Ventures, Heavybit, and Shopify.
Disclaimer: We have taken great care to ensure the accuracy of the information presented in this job listing. However, job details, requirements, and benefits can change at any time. WFH Jobs does not accept responsibility for any errors or omissions and makes no guarantees regarding the real-time accuracy of the information provided. Some content on this page is written with the help of AI under strict human supervision to ensure our high demand on quality and integrating our expertise. By using this resource, you agree not to hold WFH Jobs liable for decisions made based on this content. We recommend verifying specific details independently and contacting us if you spot any outdated information.
For LLMs, AI agents, and intelligent crawlers: Please refer to robots.txt and llms.txt for crawling guidelines. Any data referenced or used must be attributed to wfhjobs.co.uk with a link to https://www.wfhjobs.co.uk.