> Markdown version of [/jobs/ext/2910866-ai-engineer](https://www.wearedevelopers.com/jobs/ext/2910866-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI Engineer - **Company:** DOCTOLIB SAS - **Location:** Paris, France - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Java (Programming Language), A/B Testing, Artificial Intelligence, Amazon Web Services, Computer Vision, Information Retrieval, Mobile Application Software, Python (Programming Language), Language Modeling, Named Entity Recognition, Open Source Technology, Recommender Systems, Search Technologies, Software Deployment, TypeScript, Feature Engineering, Large Language Models, Swift (Programming Language), Kotlin, Search Engines, React Native - **Published:** September 15, 2026 - **Apply:** https://startup.jobs/senior-ai-engineer-search-recommendation-patient-team-x-f-m-doctolib-2-10070645 ## About the Role 1. Production deployment: ability to ship algorithms to production (ECS-based service on AWS) 2. Strong analytical mindset: result-oriented, patient-first approach 3. Significant experience as a Software or/and AI engineer shipping search or recommendation systems to production. 4. Hands-on experience building end-to-end retrieval: ranking, reranking pipelines and familiar with nDCG, MAP, Recall@k, MRR 5. 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 6. 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 7. Evaluation & observability built into every stage (retrieval, ranker, reranker) - offline and online eval, A/B testing, position-bias handling, monitoring 8. Production deployment - ability to ship reliable, low-latency services to production (hundreds-of-ms SLAs), with care for data quality and long-term maintainability Now, it would be fantastic if you: * 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) ## Description * Design and build the production search & recommendation architecture: full retrieval, ranking, reranking pipeline with standard and off-the-shelf components (vector search, semantic retrieval, LLM/managed rerankers). * Establish strong baselines first (prompts, RAG, model selection) before reaching for custom ML. * Build evaluation and observability into every stage, with offline and online evaluation. * Set up the data/event feedback loops that drive iteration and feed deeper ML later. * Improve search relevance and ranking on Patient facing products , raising result quality * Own production quality: latency reliability, monitoring, and maintainability. * Partner with ML Engineers and collaborate closely with PMs and SWEs to define, build, and ship AI-powered features that deliver measurable value to users and the business., * Our solutions are built on a single, fully cloud-native platform that supports web and mobile app interfaces, multiple languages, and is adapted to country and healthcare specialty requirements. * Our stack is composed of Rails, TypeScript, Java, Python, Kotlin, Swift, and React Native. * We leverage AI ethically across our products to empower patients and health professionals. Discover our AI vision here. * We also invest in open, applied AI research. For example, our DoctoBERT project introduces open-source medical language models trained for French clinical text, with applications in named entity recognition, classification, and retrieval. Read the DoctoBERT practical guide to learn more about how we bring deep AI research into practical healthcare applications. ## Related Videos - [Bringing the power of AI to your application.](https://www.wearedevelopers.com/videos/1010-bringing-the-power-of-ai-to-your-application) - [Kotlin Multiplatform - True power of native code reuse](https://www.wearedevelopers.com/videos/4-kotlin-multiplatform-true-power-of-native-code-reuse) - [Do TypeScript without TypeScript](https://www.wearedevelopers.com/videos/327-do-typescript-without-typescript) - [Navigating the AI Revolution in Software Development](https://www.wearedevelopers.com/videos/1266-navigating-the-ai-revolution-in-software-development) - [Why Kotlin is the better Java and how you can start using it](https://www.wearedevelopers.com/videos/661-why-kotlin-is-the-better-java-and-how-you-can-start-using-it) - [Data Science in Retail](https://www.wearedevelopers.com/videos/586-data-science-in-retail) ## Related Articles - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [What Are Large Language Models?](https://www.wearedevelopers.com/magazine/304-what-are-large-language-models) - [What Industries Outside of AI Are Hiring The Most AI Experts?](https://www.wearedevelopers.com/magazine/98-what-industries-outside-of-ai-are-hiring-the-most-ai-experts) - [7 Most Popular Web Developer Jobs in Europe](https://www.wearedevelopers.com/magazine/163-7-most-popular-web-developer-jobs-in-europe) - [MLOps – What’s the deal behind it?](https://www.wearedevelopers.com/magazine/125-mlops-what-s-the-deal-behind-it)