AI Engineer

**Why Telepatia** Telepatia AI is a healthtech company on a mission to transform healthcare in Latin America and beyond. Born at Stanford and built by doctors for doctors, our platform introduces AI Healthcare Employees that work invisibly inside clinical workflows — transcribing consultations in real time, generating structured medical records, offering evidence\-based decision support, and integrating seamlessly with any current health system — all without disrupting the physician’s flow. **What You'll Do** * Design, build, and scale Python microservices (FastAPI) that handle real\-time inference and structured data processing — built to serve millions of users reliably. * Build and architect AI agent pipelines for reasoning, orchestration, and multi\-step workflows — using the right tool for the job, whether that's an existing framework or a custom solution. * Own AI systems end\-to\-end: from initial design through production, including monitoring, cost management, failure modes, and observability. * Develop data pipelines and eval dashboards to monitor, analyze, and continuously improve AI model performance in production. * Integrate models and pipelines into our core Medical Scribe product to enhance automation, reliability, and the doctor experience. * Shape and execute on ambiguous, non\-technical requests alongside clinicians, product managers, and software engineers — pushing back when needed, proposing better approaches, and shipping fast when the path is clear. * Set technical standards and raise the engineering bar for how AI systems are built and evaluated at Telepatia. **What You Have** * Senior backend engineering experience at the AI application layer — LLM orchestration, agents, and pipelines. * Hands\-on with AI frameworks (LangChain, LangGraph, PydanticAI, or similar) and production\-ready integrations across model providers, embeddings, and third\-party AI services. * Strong Python skills; FastAPI preferred. * Track record scaling AI systems to millions of users with real attention to latency, cost, and reliability. * Fluent in context engineering — RAG, vector stores, knowledge graphs, and grounding agents with large\-scale data. * Comfortable with any database stack: Postgres, Firestore, graph DBs, vector stores. * Experience with data pipelines, model evaluation, and AI observability. * Sharp problem\-solver who keeps things simple, practical, and maintainable. * Ownership mindset — you drive outcomes, not just tasks, in fast\-moving, ambiguous environments. * Bonus: healthcare/EHR data, LGPD/HIPAA compliance, or early\-stage startup experience. * Fluent in english