• Build and evolve MAIA's core product capabilities • Focus on backend and AI systems, RAG pipelines, and LLM integrations • Design, implement, and ship features from discovery to production rollout • Build and iterate on evaluation approaches for LLM features • Scout new technologies and push the team's understanding • Collaborate closely with Product, DevOps, and customer-facing teams

• 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 evaluation approaches for LLM features • Implement frontend changes needed to ship features end-to-end • Scout new technologies and approaches • Collaborate closely with Product, DevOps, and customer-facing teams

• Support AI feature development for retrieval, ranking, categorization, and generative AI features on healthcare data • Participate in AI projects from requirements gathering through deployment • Assist in model implementation and monitoring deployed models • Apply established methodologies for effective AI solutions • Work closely with product managers, senior engineers, and team members

Role Description We are looking for an Applied AI Engineer (f/m/x) to join our engineering team - someone who ships production-grade AI features end-to-end, from retrieval pipelines and agentic workflows to the APIs that power them. - Build and evolve MAIA's core product capabilities with a focus on backend and AI systems. - Design, implement, and ship features from discovery to production rollout, emphasizing backend and AI functionality. - Build and iterate on RAG pipelines, retrieval strategies, and LLM integrations, making pragmatic tradeoffs across quality, latency, and cost. - Build evaluation approaches for LLM features, including quality gates, regression detection, and observability. - Proactively scout new technologies and approaches, translating findings into production-ready solutions. - Collaborate closely with Product, DevOps, and customer-facing teams to turn requirements into high-quality, maintainable software. Qualifications - Strong backend engineering skills in TypeScript or another strongly typed language (Go, Java, Rust). - Proven experience building and shipping production REST APIs. - Strong SQL skills, ideally with PostgreSQL in production. - Hands-on experience building or operating LLM applications, ideally with exposure to RAG systems and retrieval concepts. - Commercial experience with at least one relevant LLM framework and at least one vector database. - Practical experience debugging production systems using observability tooling (logs, metrics, tracing). - Foundational understanding of cloud and DevOps concepts. - Ability to follow secure development best practices in day-to-day engineering work. - Fluent in English; German is a plus. Requirements - Strong ownership mentality - take responsibility end-to-end without needing to be managed. - People enjoy working with you due to your interaction style. - AI is part of how you work; you actively explore and experiment with models, prompts, agents, and workflows. - Pragmatic builder - ship solutions at the right level of complexity for the stage. - Prioritize based on business impact and customer value. - Comfortable working in a fast-moving startup environment with ambiguity and shifting priorities. - Clear communication with both technical and non-technical stakeholders. Nice to have - Experience with Supabase. - Experience with document analysis pipelines and preprocessing for retrieval. - Experience with automated evaluation and testing for LLM features. - Experience with LLM tracing and analytics. Benefits - A central role in the engineering team of a well-funded, fast-growing AI startup. - Short decision-making paths, real ownership, and a trusted team. - Direct impact on product quality, AI capability, and company growth. - Flexible working hours and fully remote in Germany. - Access to a WellPass fitness membership for physical and mental wellbeing. - Competitive salary of 75,000 - 85,000 EUR and VSOP (Virtual Stock Option Plan) participation opportunities. - Remote-first company culture with team events and planning sessions covered. Hiring Timeline We are aiming to have this role filled by May 2026. The process consists of three stages: an intro call (30min), a technical interview (90min), and a final conversation with leadership. If this role sounds like the right next step for you, we would love to hear from you.