Senior AI Engineer (Healthcare or clinical domain experience)

⚠️ Please apply only if you have healthcare or clinical domain experience.
About Telepatia
Telepatia (https://telepatia.ai/) is a healthtech company on a mission to transform healthcare in Latin America and beyond. It was born at Stanford and built by doctors for doctors.
Its platform introduces AI Healthcare Employees that work invisibly inside clinical workflows. They:
Transcribe consultations in real time
Generate structured medical records
Offer evidence-based decision support
Integrate with any existing health system
All of this happens without disrupting the physician’s flow.
About the role
You’ll take clinical AI agents that already run in production and push them to state of the art. That means ontologies that make decision support deterministic, small models trained to specialize the stack, routers that match task difficulty to compute, and evaluation that finds what standard frameworks miss.
It’s a small team working on hard problems, building systems doctors across Latin America use every day.
What you’ll do
Design clinical ontologies and structured knowledge representations that agents consume, so decision support is deterministic and auditable rather than “the model usually gets it right”
Fine-tune and distill small LLMs to specialize and speed up the agent stack, from data curation to deployment
Decide when a problem needs better context, training, or deterministic code, and justify the call on quality, latency and cost. Context engineering here is measured engineering (retrieval, compression, memory, structure), not prompt tweaking.
Build router models and task decomposition: make the easy 80% cheap and fast, and the hard 20% correct
Push evaluation past the standard playbook with adversarial and counterfactual evals, calibrated LLM-as-judge, failure taxonomies and uncertainty estimation. The current framework is already good; your job is to find what it misses.
Own these systems in production (monitoring, cost, failure modes) and set the bar for how agents are built and evaluated
What you bring
Healthcare or clinical domain knowledge
Experience in fast-paced environments
Senior, hands-on depth in this exact work: models you trained end to end where the result mattered, evaluation systems that caught what standard metrics didn’t, and agents you shipped and kept running
Clear judgment on context versus training, and when each is the right answer
Fluency in context engineering: RAG, vector stores, knowledge graphs, grounding agents against large-scale data
The ability to look at a clinical rule and decide what belongs in code, in an ontology, or in the model, and to defend that split
Strong Python, and the ability to read research and tell which results will hold up in production
AI-native habits: you code with AI tools daily and get real leverage from them
Fluent English
Healthcare or clinical domain knowledge
Experience in fast-paced environments
Location
Remote from Sao Paulo, Bogota, Mexico City, Buenos Aires, or Chile.

Work arrangement
Yes