Lead AI Full Stack Engineer

Remote | Full-time About the role We are a small, fast-moving team looking for our technical lead. You take an idea from the founders, shape it into an architecture, and ship it to production. You work directly with our Designer (Figma) and with the founders on what gets built and why. There is no engineering manager above you translating tickets, because you are the person making the technical calls. The work sits at the intersection of modern web development and applied AI. You should be as comfortable with a database schema and a payment flow as you are with model APIs and agent workflows. This role comes with a lot of surface area and a lot of ownership. If you want a narrow ticket queue, this is not it. If you want to define the stack, build things from zero and grow a team around them, keep reading. We work quietly and share details step by step. What we are building is discussed once we have met and both sides see a fit. What you will do Own the technical architecture from idea to productionBuild and ship the full stack: frontend, backend, database, infrastructureBuild AI features end to end: LLM integrations, streaming responses, prompt and context design, evals, retries and fallbacksBuild and maintain MCP servers that connect our products and internal workflows to AI clientsDesign async pipelines for long-running AI jobs: queues, webhooks, progress states, cost control per runTranslate Figma designs into clean, precise interfacesBuild secure payment flows (Stripe), authentication, user management, and access controlSet up security fundamentals: data protection, input validation, secure APIs, rate limitingMake the calls on tooling, infrastructure, and technical trade-offs, and explain them in plain languagePush back when a request does not make technical or economic sense What we are looking for Proven full stack experience with a portfolio of products you shipped and kept running, not just prototypesStrong in React and Next.js (or a comparable modern framework)Strong backend: Node.js or Python, databases, REST or GraphQL, background jobs and queuesHands-on experience building with LLM APIs (OpenAI, Anthropic, or similar) in production, not only in side projectsExperience building MCP servers, or the ability to walk us through one you builtComfort with third-party model APIs and async generation pipelines (image, video, or audio)Experience with Stripe and with auth and security: OAuth, JWT, role-based access, encryptionSaaS product experienceYou work independently, manage your own delivery, and communicate early when something slipsYou care about the product, not only the code, and you contribute to product decisionsYou are comfortable signing an NDA and working on something that is not public yet Nice to have Experience scaling a product from zero to first paying usersFamiliarity with agent frameworks, evals, or RAG in productionYou have built something people use in your own time The setup Remote, full-time, 40 hours per week, Monday to FridayFlexible scheduling within the week, agreed calls attended, 24-hour response timeCompensation based on experience, discussed openly on the first callStart: as soon as possible How to apply Send us: Links to two or three things you built, with a sentence on what part was yoursYour GitHub or any public codeOne paragraph on the hardest technical problem you solved this year and how you solved it https://form.typeform.com/to/uMBsX8li