Senior AI Engineer - Patient Health Platform (x/f/m)
On-siteParis, Île-de-France, France
Job Summary
Design and build the production search and recommendation architecture, including full retrieval, ranking, and reranking pipelines with vector search, semantic retrieval, and LLM-based rerankers. Establish strong baselines using prompts, RAG, and model selection before custom ML, while setting up data and event feedback loops for offline and online evaluation. Improve search relevance on patient-facing products by raising result quality and ensuring production reliability through latency monitoring and maintainability. Partner with ML engineers, product managers, and software engineers to define and ship AI-powered features that deliver measurable value.
Required Qualifications
- Production deployment: ability to ship algorithms to production (ECS-based service on AWS)
- Significant experience as a Software or/and AI engineer shipping search or recommendation systems to production
- Hands-on experience building end-to-end retrieval: ranking, reranking pipelines and familiar with nDCG, MAP, Recall@k, MRR
- AI-engineering proficiency: turning foundation models and off-the-shelf components into production systems: embeddings & vector search, semantic retrieval, RAG, LLM-based or managed rerankers (e.g. Vertex AI). You can succeed without training a model from scratch
- Architecture-first approach: you build the system, baselines, evals, and feedback loops with standard tooling before reaching for custom ML, and know when to partner with ML Engineers to break a ceiling
- Evaluation & observability built into every stage (retrieval, ranker, reranker) — offline and online eval, A/B testing, position-bias handling, monitoring
- Production deployment — ability to ship reliable, low-latency services to production (hundreds-of-ms SLAs), with care for data quality and long-term maintainability
Desired Qualifications
- Experience at a B2C marketplace (e-commerce, hospitality, travel)
- Additional ML methodologies: pattern mining, recommendation systems, experimentation, or causal inference
- Have experience with search engines or information retrieval concepts
- Have exposure to learning-to-rank or feature engineering (for breaking ceilings later, alongside ML Engineers)
- Have experience in a healthcare or other regulated domain (GDPR / HDS)
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.