远程工作雷达

高级软件工程师,AI增长

Senior Software Engineer, AI Growth

AI开发工程市场运营限定地区(需当地身份)
公司Sanity
薪资未公开
工作地点Remote in the United States / San Francisco Bay Area
地域资格限定地区(需当地身份)
时区要求无特别要求
用工类型FullTime
发布时间2026-02-14
数据来源Ashby
前往企业招聘页投递 →
注意地域限制:该职位明确限定在 Remote in the United States 招聘。如果你是位于中国大陆的求职者,通常需要当地工作身份才能投递,或需与雇主确认是否接受独立合同(Contractor)形式合作。

在Sanity,我们正在构建AI驱动的内容运营的未来。我们的AI内容操作系统让团队可以按业务需求自由地建模、创建和自动化内容,加速数字开发并提升内容运营效率。Linear、Figma、Riot Games、Anthropic、Spotify、Arc’teryx和Morningbrew等公司正在使用Sanity来驱动和自动化他们的内容运营。

在这个职位中,你将帮助构建Sanity的AI原生开发全栈——从推进我们的模型上下文协议(MCP)服务器到交付能够生成Sanity应用、Studios和全栈前端的智能系统。你将与设计师、产品经理和工程师密切合作,快速推进、持续实验,并将新兴的AI能力转化为实际产品。如果你是那种会熬夜研究新模型发布,并且思考的是可能性而非已有成果的人,那么这就是你的职位。

以下是我们在近期完成的一些工作:

- Sanity MCP Server https://mcp.sanity.io – 我们的远程MCP服务器,现已正式可用 https://www.sanity.io/blog/sanity-remote-mcp-server-is-generally-available,并被列为Vercel v0中的八个官方MCP服务器之一。

- Sanity Agent Toolkit https://github.com/sanity-io/agent-toolkit – 通过MCP暴露的代理规则,以及带有技能和斜杠命令的Claude代码插件。

- CLI中的自动配置MCP https://www.sanity.io/docs/changelog/beb93f6c-7913-4ea7-8bbb-847ba7b51b19 – Sanity CLI会自动检测代码编辑器并为你配置MCP服务器。

你将负责以下工作

- 推进我们的MCP服务器——添加新的功能、工具和集成,使AI代理能够深度与Sanity的内容平台交互。

- 构建智能开发者工具——交付系统,能够在最少人工指导的情况下生成Sanity应用和Studios,以及前端代码。

- 设计并运行评估——使用Braintrust构建评估套件,以捕捉回归问题、衡量改进效果,并根据提示和模型变化做出数据驱动的决策。

- 构建Sanity MCP应用 https://blog.modelcontextprotocol.io/posts/2025-11-21-mcp-apps/ – 在MCP协议之上为平台如ChatGPT(使用新的ChatGPT Apps SDK https://developers.openai.com/apps-sdk/build/chatgpt-ui)和Claude创建丰富的React界面。

- 每天在技术栈中穿梭——有一天你在设计一个新的MCP工具,第二天你就可能在处理其他任务。

查看英文原文

At Sanity, we're building the future of AI-powered Content Operations. Our AI Content Operating System gives teams the freedom to model, create, and automate content the way their business works, accelerating digital development and supercharging content operations efficiency. Companies like Linear, Figma, Riot Games, Anthropic, Spotify, Arc’teryx and Morningbrew are using Sanity to power and automate their content operations.

In this role, you'll help build the full vertical for AI-native development at Sanity – from advancing our Model Context Protocol (MCP) server to shipping agentic systems that can scaffold Sanity apps, Studios, and full-stack frontends. You'll work closely with a designer, product manager, and fellow engineers to move fast, experiment constantly, and turn emerging AI capabilities into real products. If you're the kind of person who stays up late tinkering with new model releases and thinks in terms of what's possible rather than what's been done before, this is your role.

Here's some of what we've shipped recently:

- Sanity MCP Server https://mcp.sanity.io – our remote MCP server, now generally available https://www.sanity.io/blog/sanity-remote-mcp-server-is-generally-available and listed as one of eight official MCP servers in Vercel's v0.

- Sanity Agent Toolkit https://github.com/sanity-io/agent-toolkit – agent rules exposed via MCP, plus a Claude Code plugin with skills and slash commands.

- Auto-configured MCP in the CLI https://www.sanity.io/docs/changelog/beb93f6c-7913-4ea7-8bbb-847ba7b51b19– the Sanity CLI automatically detects code editors and configures the MCP server for you.

WHAT YOU WILL DO

- Advance our MCP server – add new capabilities, tools, and integrations that let AI agents interact deeply with Sanity's content platform.

- Build agentic developer tools – ship systems that can generate Sanity apps and studios, as well as frontend code with minimal human guidance.

- Design and run evals – build evaluation suites using Braintrust to catch regressions, measure improvements, and make data-driven decisions about prompt and model changes.

- Build a Sanity MCP app https://blog.modelcontextprotocol.io/posts/2025-11-21-mcp-apps/ – create rich React interfaces on top of the MCP protocol for platforms like ChatGPT (using the new ChatGPT Apps SDK https://developers.openai.com/apps-sdk/build/chatgpt-ui) and Claude.

- Move across the stack daily – one day you're designing a new MCP tool, the next you're polishing a React component or deploying a new microservice.

- Apply prompt engineering craft – diagnose why models fail, steer them effectively, and build intuition for what makes prompts work at scale.

- Ship production AI features – write clean, well-tested TypeScript and turn experiments into reliable capabilities that thousands of developers use.

- Collaborate with the team – work closely with design, product, and engineering to iterate quickly and share what you learn.

ABOUT YOU:

- Based in Remote US or San Francisco / Bay Area – if you are in San Francisco/ Bay Area, you should be able to work at least 2 days a week from the office.

- Strong TypeScript, React, and Node.js skills – you're comfortable moving between frontend and backend, and a pure specialist profile isn't what we're after.

- Shipped AI-powered code to production – whether at work or through side projects, you've built real things with OpenAI, Anthropic, or Vercel AI SDKs.

- Actively using MCP in your workflow – you've enhanced your own development with MCP servers. Bonus if you've built one yourself.

- Fluent in the current AI landscape – you can articulate the differences between Claude Opus 4.5, Gemini 3, and GPT-5.2, and you have opinions on tools like Cursor, Claude Code, Lovable, and v0.

- Hungry and curious – you're obsessed with the craft, experimenting constantly, and energized by how fast this space moves.

- Strong prompt intuition – you can "decode" why a model is hallucinating or ignoring instructions without relying solely on automated evals.

- Collaborative and clear communicator – you work well with designers and product managers, and you can explain complex AI concepts simply.

Not sure you meet every requirement? If you're building in this space and can't stop thinking about what's next, we want to hear from you.

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

WHO WE ARE:

Sanity https://www.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 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, citizenship, marital status, disability, or gender identity.

本页面信息整理自 Ashby,版权归原发布方所有。职位可能随时关闭,投递请以原始页面为准。 本站只做信息聚合展示,不参与招聘流程,也不向求职者收取任何费用。

该公司其他在招职位

收入运营总监

SanityRemote in the United StatesFullTime6 天前
市场运营职能支持限定地区(需当地身份)

销售赋能总监

SanityRemote in the United StatesFullTime6 天前
市场运营职能支持限定地区(需当地身份)

← 返回全部职位