Your Impact
We are looking for a Senior Machine Learning Engineer to join the ML Engineering team in Patient Solutions .
Your mission will be to improve how people access quality care and manage their health over time by building and leading AI and ML systems that create real, measurable impact. You will work in a feature team developing intelligent patient-facing solutions, from smart practitioner discovery to long-term care management, playing a key technical role in shaping how we scale our AI capabilities across Europe.
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
Your responsibilities include but are not limited to:
- Design and implement ML and AI solutions aligned with patient product goals, covering search, retrieval, and personalized care pathways
- Build and maintain large-scale retrieval pipelines, including hybrid search, embedding systems, vector databases, and multi-stage re-ranking architectures
- Develop, fine-tune, and evaluate LLM and VLM models using techniques such as knowledge distillation, Mixture-of-Experts (MoE) architectures, and prompt engineering
- Build and orchestrate agentic AI systems, integrating external data and capabilities through tools and MCP-based integrations
- Define metrics aligned with product goals, run controlled end-to-end experiments using W&B, MLFlow, or Braintrust, and communicate findings to guide product and technical decisions
- Deploy solutions to production in collaboration with our ML platform team, ensuring reliability, observability, and performance at scale, and act as a technical reference to elevate the team's standards and practices
Who you are
Before 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.
You'll be a great fit if you:
- You have 7+ years of experience in Machine Learning, Deep Learning, or AI Engineering, with a strong track record of taking models from prototype to production at scale
- You have strong experience in Information Retrieval and modern retrieval stacks: hybrid search (sparse + dense), large-scale embeddings and vector databases, multi-stage retrieval and re-ranking pipelines, RAG architectures, and tool/MCP-based integrations
- You are proficient in LLM and VLM application development: fine-tuning, MoE architectures (via LiteLLM or Model Garden), knowledge distillation, prompt engineering, and systematic benchmarking of LLM/VLM systems
- You have hands-on experience building and orchestrating agentic AI systems (e.g., using ADK)
- You demonstrate strong scientific rigor: designing metrics aligned with product goals, running controlled experiments, and communicating result