Senior Full-Stack AI EngineerLocation:Brazil(Remote)About Sphise TechnologiesSphise Technologies is a global outsourcing and talent solutions company, partnering with high-growth businesses to build strong, high-impact teams across finance, technology, and operations. Our trusted high-growth technology partner is building a production AI platform that transforms disconnected data into measurable business growth. With customers already onboarding and the platform live in production, they are hiring aSenior Full-Stack AI Engineerto scale their next-generation AI systems.Position Overview:We are seeking aSenior Full-Stack AI Engineerto own the intersection ofagentic AIandmodern web development. You will build theintelligent backend powering a multi-agent systemand theinteractive frontend delivering real-time AI experiences. This role requires strongarchitectural judgment— the platform runs onVercel, and decisions aroundcaching, bandwidth, cost efficiency, and production reliabilityare critical. If you are excited about buildingAI agents that work in production, designingstreaming chat experiences, and solving complexorchestration challenges, this is the opportunity for you.What You'll Do:Design and optimizeproduction prompts for LLMsand buildmulti-agent workflowswithsmart routing, specialization, and human-in-the-loop approval gates Buildstateful agent workflowswithplanning, execution, and observation loops— making sure agents reliably follow structured steps even when users go off-script Createstreaming chat UIswithreal-time rendering, tool call visualization, and interactive artifacts Connect agents toanalytical databasesforlive data retrieval, SQL generation, and knowledge base access through RAG pipelines Ownperformance across the full stack—caching strategies, bandwidth optimization, and keeping Vercel costs under control ImplementLLMOps practicesincludingprompt versioning, observability, and cost tracking.What You Bring3–5+ years of progressive experience in full-stack development. Strong TypeScript skills across frontend, backend, and agent logic Production experience with React or Next.js (App Router, Server Components, API routes) Hands-on work with LLM agent frameworks — LangGraph, CrewAI, AutoGen, or custom agent loops Production prompt engineering: system prompts, chain-of-thought reasoning, tool-calling patterns Direct experience with LLM APIs (OpenAI, Anthropic, or open-source models) Bachelor's degree in Computer Science, Engineering, or equivalent practical experienceNice to Have Experience with Vercel AI SDK (useChat, streamText, streaming patterns) Familiarity with durable workflow engines like Trigger.dev or Temporal Experience with RAG pipelines, vector databases, or knowledge retrieval systems Background in performance optimization for Vercel-hosted applications Experience at an early-stage startup or building a product from 0 to 1.Benefits: Competitive salary to recognise and reward your achievements. Flexible work environment. Opportunities for professional and personal growth.