All jobs
What we're looking for
- Senior backend engineering experience at the AI application layer
- Experience with LLM orchestration, agents, and pipelines
- Track record scaling AI systems to millions of users
- Fluent in context engineering (RAG, vector stores, knowledge graphs)
- Fluent in English
About the role
ABOUT THE ROLE
We're looking for a senior AI Engineer to design, build, and scale the AI systems that power our Medical Scribe product. This is an end-to-end ownership role — you'll take AI systems from initial design through to production, including monitoring, cost management, failure modes, and observability. You'll set technical standards, raise the engineering bar, and work directly alongside clinicians, product managers, and software engineers to turn ambiguous clinical needs into reliable, high-performance systems.
WHAT YOU'LL WORK ON
Python microservices at scale
Design, build, and scale Python microservices (FastAPI) for real-time inference and structured data processing, serving millions of users reliably.
AI agent pipelines
Build and architect AI agent pipelines for reasoning, orchestration, and multi-step workflows — using existing frameworks or custom solutions depending on what the problem actually requires.
End-to-end AI system ownership
Own AI systems from initial design through production — including monitoring, cost management, failure modes, and observability. You're responsible for the system, not just the code.
Evaluation and continuous improvement
Develop data pipelines and evaluation dashboards to monitor, analyse, and continuously improve AI model performance in production. Good enough at launch isn't good enough over time.
Product integration
Integrate models and pipelines into the core Medical Scribe product to enhance automation, reliability, and the doctor experience — always with clinical context in mind.
Cross-functional collaboration
Shape and execute on ambiguous, non-technical requests alongside clinicians, product managers, and engineers. Propose better approaches where you see them, and ship fast when the path is clear.
Technical standards
Set the bar for how AI systems are built and evaluated across the engineering team. Your decisions become the patterns others follow.
WHAT WE LOOK FOR
Senior backend engineering at the AI application layer
Proven experience building and operating production AI systems — not just ML models, but the full application layer around them.
LLM orchestration, agents, and pipelines
Hands-on experience designing and building LLM-based systems in production — agents, multi-step pipelines, tool use, and everything that makes them reliable at scale.
Scaled AI systems
A track record of scaling AI systems to millions of users. You've dealt with the latency, cost, reliability, and observability challenges that come with real production scale.
Context engineering
Fluent in RAG, vector stores, and knowledge graphs — and how to apply them thoughtfully rather than reflexively.
Fluent English
Strong written and spoken English — you'll work closely with an international team and need to communicate technical decisions clearly.
THE TEAM
A small, senior engineering team building real-time AI infrastructure for healthcare. The work is technically hard, the domain is consequential, and the team operates with high trust and high standards. Remote-first, based across Latin America.
We're looking for a senior AI Engineer to design, build, and scale the AI systems that power our Medical Scribe product. This is an end-to-end ownership role — you'll take AI systems from initial design through to production, including monitoring, cost management, failure modes, and observability. You'll set technical standards, raise the engineering bar, and work directly alongside clinicians, product managers, and software engineers to turn ambiguous clinical needs into reliable, high-performance systems.
WHAT YOU'LL WORK ON
Python microservices at scale
Design, build, and scale Python microservices (FastAPI) for real-time inference and structured data processing, serving millions of users reliably.
AI agent pipelines
Build and architect AI agent pipelines for reasoning, orchestration, and multi-step workflows — using existing frameworks or custom solutions depending on what the problem actually requires.
End-to-end AI system ownership
Own AI systems from initial design through production — including monitoring, cost management, failure modes, and observability. You're responsible for the system, not just the code.
Evaluation and continuous improvement
Develop data pipelines and evaluation dashboards to monitor, analyse, and continuously improve AI model performance in production. Good enough at launch isn't good enough over time.
Product integration
Integrate models and pipelines into the core Medical Scribe product to enhance automation, reliability, and the doctor experience — always with clinical context in mind.
Cross-functional collaboration
Shape and execute on ambiguous, non-technical requests alongside clinicians, product managers, and engineers. Propose better approaches where you see them, and ship fast when the path is clear.
Technical standards
Set the bar for how AI systems are built and evaluated across the engineering team. Your decisions become the patterns others follow.
WHAT WE LOOK FOR
Senior backend engineering at the AI application layer
Proven experience building and operating production AI systems — not just ML models, but the full application layer around them.
LLM orchestration, agents, and pipelines
Hands-on experience designing and building LLM-based systems in production — agents, multi-step pipelines, tool use, and everything that makes them reliable at scale.
Scaled AI systems
A track record of scaling AI systems to millions of users. You've dealt with the latency, cost, reliability, and observability challenges that come with real production scale.
Context engineering
Fluent in RAG, vector stores, and knowledge graphs — and how to apply them thoughtfully rather than reflexively.
Fluent English
Strong written and spoken English — you'll work closely with an international team and need to communicate technical decisions clearly.
THE TEAM
A small, senior engineering team building real-time AI infrastructure for healthcare. The work is technically hard, the domain is consequential, and the team operates with high trust and high standards. Remote-first, based across Latin America.
About Telepatia
We're a healthtech company on a mission to transform healthcare in Latin America and beyond. Built by doctors for doctors, our platform deploys AI directly inside clinical workflows — transcribing consultations in real time, generating structured medical records, providing evidence-based decision support, and integrating with existing health systems without disrupting the physician's flow. We operate across Brazil and Colombia, serving millions of users. The AI layer is the core of what we build — and the engineering bar here reflects that.