Senior AI Platform Engineer

Join Afresh as a Senior AI Platform Engineer, where you'll build the AI and data platform that powers our products. You'll design and operate the knowledge graph and ontology, build retrieval systems, and create LLM-powered agents. You'll also own evaluation, quality, and the data foundation. This is a senior, 0-to-1 platform role that requires a strong background in data engineering, production software, and LLM systems.

• Construire la couche de connaissance et de récupération, concevoir et exploiter le graphe de connaissances et l'ontologie qui capturent la relation entre les données alimentaires.
• Développer et servir la plateforme d'agents, construire des agents alimentés par LLM (utilisation d'outils, raisonnement multi-étapes, orchestration) et l'infrastructure de service pour les exécuter de manière fiable.
• Assumer la responsabilité de l'évaluation, de la qualité et de la fondation des données, mettre en place des ensembles d'évaluation, des ensembles de données et des outils d'évaluation.
• Comfort in the messy middle of AI systems — retrieval quality, latency and cost trade-offs, non-determinism — and the instinct to build the guardrails and evals that make them trustworthy
• A platform mindset: you build for leverage and clean interfaces, and you thrive in ambiguity in a fast-moving space
• Solid data-engineering and data-platform foundations: pipelines, data modeling, and a modern cloud data stack (Databricks/Spark, MLflow, cloud warehouses)
• 3+ years building production software, data, or ML systems; an excellent engineer with strong systems and API design (Python)
• Hands-on production experience with LLM systems: retrieval/RAG, agents and tool-use, prompt and context engineering — and, critically, evaluation. You measure quality; you don't eyeball it
• Knowledge graphs, ontologies, or semantic layers in production; graph databases
• Vector stores (pgvector, Pinecone, Weaviate, etc.) and hybrid search
• MCP or similar tool/context protocols; agent frameworks (e.g., LangGraph)
• MLOps and model serving at scale; experimentation and observability tooling for LLM systems
• Experience in grocery, retail, or other complex enterprise data domains