Engineer, Technology Deployment

About Telepatia Telepatia AI is building an AI Doctor to radically improve healthcare.

We recently raised the largest LatAm seed round of $9M, backed by top global investors.

Our team comes from Stanford, Microsoft, MD Anderson, Houston Methodist, and Alice, and we're on a mission to transform how clinical data is captured and used.

Healthcare has two fundamental sources of truth : images and conversations.

While most technology has focused on images, 99% of real medical decisions are made through voice.

Telepatia is capturing that voice data and turning it into structured, reliable clinical intelligence—unlocking the foundation for an AI-first healthcare system.

We are assembling one of the most talent-dense technical teams in Latin America, with the ambition of building the "Manhattan Project" of AI in healthcare.

Mission of the Role As an AI Engineer at Telepatia, your mission is to design, build, and deploy AI systems that turn unstructured clinical conversations into structured, reliable medical intelligence.

You'll work across the stack—from backend Python microservices and LLM orchestration to lightweight front-ends and data pipelines—integrating the latest in AI research into production workflows used by doctors daily.

You'll be part of a small, elite team where each engineer's output directly impacts the accuracy of our AI systems, the speed of our clinical documentation, and ultimately, patient care across Latin America.

This is a role for builders who want to ship fast, work with autonomy, and push the boundaries of what's possible in applied AI.

What You'll Do Design, build, and scale Python microservices (FastAPI) that handle real-time inference and structured data processing.

Build AI agent pipelines for reasoning, orchestration, and multi-step workflows using tools like LangChain or CrewAI.

Develop data pipelines and eval dashboards to monitor, analyze, and improve AI model performance.

Collaborate closely with clinicians, product managers, and software engineers to turn ambiguous requests into production-ready AI features—often in less than a day.

Integrate models and pipelines into our core Medical Scribe product to enhance automation, reliability, and doctor experience.

Contribute to key technical decisions around LLM infrastructure, evaluation, scalability, and deployment.

Must-Haves Strong backend experience in Python, with a focus on microservices (FastAPI preferred).

Experience building at the AI application layer : LLM orchestration, agents, and pipelines (LangChain, CrewAI, or similar).

Frontend familiarity with React / Tailwind or Flutter for rapid prototyping and data visualization.

Experience building and maintaining data pipelines and evaluation dashboards for AI models.

High product velocity : you prioritize shipping value quickly over theoretical perfection.

Ability to take ambiguous, non-technical requests and turn them into working production features in less than a day.

Strong ownership mindset, curiosity, and comfort working in a fast-paced, high-ambiguity environment.

Nice-to-Haves Background in hard sciences such as Physics or Mathematics.

Experience with vector databases, RAG architectures, or model evaluation frameworks.

Prior work with healthcare data, EHR systems, or HIPAA / LGPD compliance.

Prior startup experience in high-growth or early-stage environments.