高级软件工程师, 内容代理
Senior Software Engineer, Content Agent
我们正在招聘一位高级工程师，负责Content Agent——Sanity的结构化内容操作层。这是将内容工作（批量编辑、审计、翻译、发布）转化为代理实际可执行任务的系统。它存在于Dashboard、Studio、Slack以及无头API之后。如果你曾参与过必须为真实用户服务而非仅在演示中运行的AI系统，请继续阅读。
在Sanity，我们构建了一个由AI驱动的内容操作系统，使团队能够以业务实际运行的方式建模、创建和自动化内容。SKIMS、Figma、Riot Games、Anthropic、COMPLEX、Nordstrom和Morningbrew都在使用该系统进行内容运营。
Content Agent是产品中理解结构化内容的部分——包括模式、引用、字段类型、验证规则，并且可以被信任正确地对其进行操作。你将使用TypeScript和React进行全栈产品开发：MCP工具和集成、代理编排、系统提示、评估以提高整个系统的可靠性。该团队的工程师负责自己的领域，并与产品团队紧密合作决定下一步要构建什么。
你将从事以下工作：
- 全栈产品开发：Dashboard中的React界面、API、后端服务。
- MCP工具和集成，扩展代理的功能。
- 代理循环：决定代理做什么、按什么顺序做、何时需要引入人工干预的编排逻辑。
- 系统提示。我们将这些视为真正的工程构件，而不是文件顶部的一条注释。
- 评估和实验，以衡量并改进实际使用中的可靠性。
- GROQ，Sanity的内容查询语言——用它让代理深入理解结构化内容。
- 与产品和设计一起塑造Content Agent的未来。这里有很多发挥空间。
关于你：
- 地点：英国伦敦或挪威奥斯陆（每周2-3天办公室办公）
- 精通TypeScript和React，能在整个技术栈（前端、API、后端）中自如工作。你不希望被限制在一个层面。
- 你有在生产环境中部署基于LLM的系统经验。你知道困难之处不在于让模型完成一次任务；而是在于让每个用户都能得到正确的结果。
- 你具备系统思维。面对新的代理功能时，你会思考用户意图、边缘情况、故障模式，以及它们对架构意味着什么：代理知道什么、拥有哪些工具、何时需要升级。
- 你写作能力强，并且关心为什么一种表达方式有效而另一种无效。一个代理的输入输出直接影响用户体验。
查看英文原文
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.
WHAT YOU'D BE DOING:
- Full-stack product work: React interfaces in Dashboards, APIs, backend services.
- MCP tools and integrations that extend what the agent can do.
- Agent loops: the orchestration logic that decides what the agent does, in what order, and when to bring a human in.
- System prompts. We treat these as real engineering artifacts, not a note at the top of a file.
- Evals and experiments to measure and improve reliability in real usage.
- GROQ, Sanity's content query language - using it to give the agent a deep understanding of structured content.
- Shaping what Content Agent becomes, with product and design. There's a lot of latitude here.
ABOUT YOU:
- Location: London, UK or Oslo, Norway (in-office 2–3 days/week)
- Strong TypeScript and React, comfortable across the stack (frontend, APIs, backend). You don't want to be boxed into one layer.
- You've shipped LLM-based systems in production. You know the hard part isn't getting a model to do something once; it's getting it to do the right thing for every user who shows up.
- You think in systems. Given a new agent capability, you think through user intent, edge cases, failure modes, and what that means for the architecture: what the agent knows, what tools it has, when it escalates.
- You write well and you care about why one phrasing works where another doesn't. An agent's instructions are prose running on a system that reads literally. Writing them well takes a feel for how language lands, not just what it says - who "you" refers to, what's implied versus explicit, how a sentence will actually be parsed.
- You're comfortable with probabilistic systems. Improving an LLM product means running experiments, designing evals, reading results statistically, and not chasing individual failures when the aggregate trend is what matters. You've moved past "it compiles or it doesn't."
- Real experience with, or real curiosity about, MCP, tool-use patterns, and agent architectures.
- You care about craft in code, in writing, and in the products you ship.
Nobody checks every box. We're especially interested in people from non-traditional backgrounds - writing, interaction design, liberal arts - who've built real engineering skills on top. Some of the best agent work we've seen comes from people who understand language and how people actually work, not just systems architecture. If this sounds like you, send something in.
WHAT WE CAN OFFER:
- A highly-skilled, inspiring, and supportive team
- Positive, flexible, and trust-based work environment that encourages long-term professional and personal growth
- A global, multi-culturally diverse group of colleagues and customers
- Comprehensive health plans and perks
- A healthy work-life balance that accommodates individual and family needs
- Competitive stock options program and location-based salary
WHO WE ARE:
Sanity.io http://Sanity.io is a modern, flexible content operating system that replaces rigid legacy content management systems. One of our big differentiators is treating content as data so that it can be stored in a single source of truth, but seamlessly adapted and personalized for any channel without extra effort. Forward-thinking companies choose Sanity because they can create tailored content authoring experiences, customized workflows, and content models that reflect their business.
Sanity recently raised an $85m Series C led by GP Bullhound and is also backed by leading investors like ICONIQ Growth, Threshold Ventures, Heavybit and Shopify, as well as founders of companies like Vercel, WPEngine, Twitter, Mux, Netlify and Heroku. This funding round has put Sanity in a strong position for accelerated growth in the coming years.
You can only build a great company with a great culture. Sanity is a 200+ person company with highly committed and ambitious people. We are pioneers, we exist for our customers, we are hel ved, and we love type two fun! Read more about our values here! https://www.sanity.io/blog/our-sanity-values
Sanity.io pledges to be an organization that reflects the globally diverse audience that our product serves. We believe that, in addition to hiring the best talent, a diversity of perspectives, ideas, and cultures leads to the creation of 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.