AI | HealthTech | LLM Systems | Real-Time Inference
SnapshotJoin a fast-scaling AI healthtech company building real-time systems that operate directly inside clinical workflows — from transcription to structured medical records and decision support.You'll design and scale AI systems used by millions, powering a new generation of AI Healthcare Employees that work seamlessly alongside doctors.This is not experimentation — this is production-grade AI at scale in real-world environments.What You'll Do
Design and scale Python microservices (FastAPI) for real-time AI inference
Build and orchestrate LLM agent pipelines (multi-step reasoning workflows)
Own AI systems end-to-end:Architecture deployment monitoring optimizationDevelop data pipelines + evaluation systems for AI performanceIntegrate AI systems into core healthcare productsTranslate ambiguous requirements into scalable technical solutionsTech Stack
Python, FastAPI
LangChain, LangGraph, PydanticAI
PostgreSQL, Firestore, Vector DBs, Graph DBs
RAG, AI Observability, Data Pipelines
What We're Looking For
Senior backend / AI engineer with hands-on LLM production experience
Proven experience scaling AI systems to large user bases (millions)Strong expertise in:LLM orchestrationAgentic workflowsContext engineering (RAG, embeddings, vector stores)Experience building real-time inference systemsFluent in EnglishBonus:Healthtech or regulated industry experienceAI observability / evaluation systemsStartup experienceCompensation & Benefits$100,000 – $180,000 (USD)High-impact role in a fast-growing AI healthtech companyWork on real-world AI systems with measurable impactLocation & EligibilityHybrid | São PauloMust be based in BrazilMust have valid work authorizationComfortable with hybrid work model (São Paulo)Ideal Candidate ProfileHas built LLM-based systems in production (not just prototypes)Thinks in systems, scale, and reliability — not just promptsComfortable with ambiguity + product-driven developmentStrong ownership mindset with fast executionWhy This Role
Build AI systems deployed to millions of users
Work on LLM agents, pipelines, and real-time inference systems
Direct impact on clinical workflows and healthcare outcomes
Operate in a high-ownership, fast-shipping environment
Collaborate with clinicians, product, and engineering teams
If you're building AI systems that go beyond demos — and want to deploy real, intelligent systems into environments where they truly matter — this is where you do it. Apply now...
