• Conception et développement de solutions IA en Python. • Mise en place de pipelines RAG (Retrieval Augmented Generation). • Exploitation du cloud AWS et en particulier des services IA/LLM (ex. Bedrock). • Intégration d’outils IA et d’orchestration (N8N, OpenAI, Claude, …). • Collaboration avec les équipes produit, data et dev. • Veille technologique sur les innovations IA et proposition d’idées/concepts.

• Build and evolve MAIA's core product capabilities • Focus on backend and AI systems • Design, implement, and ship features from discovery to production rollout • Build and iterate on RAG pipelines, retrieval strategies, and LLM integrations • Build evaluation approaches for LLM features • Proactively scout new technologies and translate findings into production-ready solutions • Collaborate closely with Product, DevOps, and customer-facing teams

• Design and build the core systems powering Jimdo Companion, including agent orchestration, recommendation engines, and scalable APIs. • Develop AI-powered features that automate real business tasks and improve customer outcomes. • Build high-quality backend services and engaging frontend experiences using modern full-stack technologies. • Design, evaluate, and optimise LLM-powered workflows, prompts, guardrails, and agent coordination. • Build reusable AI platform capabilities that empower other engineering teams to create AI-enabled products. • Partner closely with Product Managers, Designers, Data Analysts, and engineers to deliver customer-centric solutions. • Champion AI-augmented software development by leveraging modern AI coding assistants and sharing best practices across the engineering team.

• Design, develop and deliver AI-powered features end-to-end: from proof of concept to production on our Partner's stack (Angular, Node/TypeScript, PostgreSQL, Azure) • Evaluate and integrate AI/ML services, APIs, and open-source models to solve real customer problems (document processing, root-cause analysis, ERP/MES integrations) • Shape the AI/ML tech stack with real ownership over tools, frameworks, and architecture • Build and maintain eval frameworks to ensure AI outputs meet quality, reliability, and safety standards • Collaborate with product and engineering, identify high-impact AI opportunities, and grow AI competency across the team