Applied AI Engineer: Autonomous Office Ops for Healthcare

ebro foods netherlands; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

ebro foods Netherlands is hiring an engineer to build AI agents that run doctors' offices. You’ll work on production systems handling real money and patient data, spanning the full stack from agent architectures to data pipelines and infrastructure for reliability.

The role emphasizes building for reliability, diagnosing live incidents, and automating repetitive work. You’ll design schemas and pipelines for large-scale datasets across databases, caches, proxies, and job orchestration systems.

Qualifications

• Experience building and deploying AI systems for production environments.
• Focus on reliability and correctness, not just features.
• Ability to diagnose live production incidents with minimal disruption.
• Ability to automate repetitive tasks and build safe tooling.
• Experience designing data schemas and pipelines for large datasets.

Responsibilities

• Build AI agents that run doctor offices and handle real workflows.
• Maintain production systems handling real money and patient data for thousands of practices.
• Work across the full stack: agent architectures, data pipelines, evals, and infra.
• Diagnose and resolve live production incidents with minimal disruption.
• Design scalable data schemas and pipelines for large datasets.

Skills

AI systems

Production reliability

Full-stack engineering

Data pipelines

Tools

Python

PostgreSQL

Redis

TypeScript

React

Tailwind

Google Cloud Platform

Vercel

Linear

Slack

Notion

Job description

ebro foods Netherlands is hiring an engineer to build AI agents that run doctors' offices. You’ll work on production systems handling real money and patient data, spanning the full stack from agent architectures to data pipelines and infrastructure for reliability.

The role emphasizes building for reliability, diagnosing live incidents, and automating repetitive work. You’ll design schemas and pipelines for large-scale datasets across databases, caches, proxies, and job orchestration systems.