Senior/Staff AI Engineer
Pubblicato il 11-10-2026 - Doctolib in Romano di Lombardia
Set a new pulse for healthcare We are looking for a Senior or Staff AI Engineer to join the Remote Care stream at Doctolib. Your mission will be to build AI-powered tools that transform how healthcare professionals deliver care beyond in-person encounters — from intelligent patient messaging to telehealth experiences. You will work in a feature team developing agentic systems across the Patient Messaging platform and Telehealth software, contributing directly to reducing care team workload and improving patient access to continuous care. Working in the tech team at Doctolib means building innovative products and features to improve the daily lives of care teams and patients.
What you'll do
- Design, ship, and operate production-grade agentic systems powering Remote Care stream products, with strong observability, fallback mechanisms, and fail-safe behaviors
- Build and improve AI agents, orchestration systems, and core agentic capabilities including memory, reasoning, tool adapters, and multi-agent coordination
- Partner with Machine Learning Engineers to design and implement evaluation pipelines, security/safety guardrails, and metrics — taking ownership of operational AI projects as data science teams focus on exploratory research
- Own performance, observability, and security: monitoring dashboards, SLO/SLI definition, and security posture, with a particular focus on medical data sensitivity
- Contribute to full-stack development when needed to deliver end-to-end features for healthcare professionals
- Mentor and enable software engineers to build confidently in an agentic AI world
Who you areBefore you read on: if you don't have the exact profile described below, but you feel this job description matches your skill set, we still encourage you to apply.
- Have 4+ years of experience as a software engineer, with hands-on experience in AI/ML systems, including going through the full lifecycle of an AI product from evaluation and launch to production iterations
- H