Full Stack AI Engineer | Onsite in San Francisco | Local Candidates Only, 5

We are partnering with an early-stage, cutting-edge AI startup in San Francisco to hire a Full Stack AI Engineer with strong zero-to-one product-building experience.This is a fully onsite position. Candidates must currently live in the San Francisco Bay Area and be able to work from the company’s San Francisco office five days per week. Please do not apply if you are seeking remote or hybrid work.About the RoleOur client is looking for a highly hands-on engineer who can help build and launch AI-native products from the ground up. You will work closely with the founders to turn ideas into production-ready applications and help shape the company’s technical foundation.The right candidate is comfortable working across frontend, backend, infrastructure, and AI systems. You should enjoy fast-moving startup environments, unclear requirements, rapid iteration, and taking full ownership of what you build.ResponsibilitiesBuild, test, launch, and improve full-stack products from zero to oneDevelop modern frontend applications using React, Next.js, or similar technologiesBuild backend services, APIs, databases, and integrationsCreate AI-powered features using large language models and multimodal modelsBuild AI agents that can use tools, complete workflows, and interact with external systemsDevelop retrieval-augmented generation, embeddings, vector search, and knowledge systemsIntegrate voice AI, speech-to-text, text-to-speech, or real-time conversational systemsImplement model routing, structured outputs, tool calling, and human approval workflowsBuild evaluation, monitoring, and testing systems for AI performanceImprove application speed, reliability, scalability, security, and AI inference costsWork directly with founders, users, and product stakeholdersHelp make product, architecture, and technology decisionsQualifications4 or more years of professional software engineering experienceProven experience building and launching a product from zero to oneStrong experience across both frontend and backend developmentExperience working at an early-stage startupStrong skills in TypeScript, JavaScript, React, and Next.jsBackend experience with Node.js, Python, FastAPI, Go, or similar technologiesExperience with PostgreSQL, APIs, cloud infrastructure, and production deploymentsHands-on experience integrating large language models into production applicationsExperience with AI agents, RAG, tool calling, embeddings, or multimodal AIStrong product judgment and the ability to work with limited directionAbility to move quickly while maintaining high engineering standardsPreferred ExperienceOpenAI, Anthropic, Gemini, or open-source AI modelsModel Context Protocol and agent orchestration frameworksLangGraph, LlamaIndex, Vercel AI SDK, or similar toolsVector databases such as Pinecone, Qdrant, Weaviate, or pgvectorVoice AI, WebSockets, WebRTC, or real-time streaming systemsAI evaluations, observability, prompt injection protection, and model securityDocker, AWS, Google Cloud, Azure, or serverless infrastructureExperience as an early, founding, or first engineering hireIdeal CandidateYou are a builder who prefers creating new products over maintaining mature systems. You are comfortable wearing multiple hats, making decisions quickly, and turning incomplete ideas into products that customers can use.You understand that strong AI products require more than connecting to a model API. You know how to build dependable workflows, evaluate output quality, manage latency and cost, and create safeguards around AI-generated actions.Location RequirementThis role is onsite in San Francisco five days per week.Candidates must already live within a reasonable commuting distance of San Francisco. Remote, hybrid, relocation-dependent, and out-of-area candidates will not be considered.Type: direct hire