Senior AI Engineer - Berlin (On-Site)

Das ist der Job

Optimize for performance and scale: Improve latency, cost-efficiency, and robustness of AI systems in production.

Darum lohnt es sich

A compelling product with real edge: mama health is building an AI-driven platform grounded in real patient experiences — highly differentiated and solving real problems in healthcare Cutting-edge challenges: Work on real LLM, RAG, and agent systems in production — not just prototypes High ownership: You’ll shape core parts of the product and how we build AI systems as a company Strong market pull: Work with leading pharma companies on high-impact use cases Ownership and growth: Fast learning curve, real responsibility, and the chance to define our AI stack Competitive package: Salary + equity Berlin-based team: Full in-office collaboration Perks: Team events, offsites, Wolt dinners & rides home when working late #J-18808-Ljbffr Your mission (This role requires you to be based in Berlin) As aSenior AI Engineerat mama health, you will build and own the core AI systems powering our product — from patient-facing experiences to our Pharma Platform.

You will: Design and ship production-grade AI systems: Build scalable LLM-based systems, including workflow agents and multi-agent architectures, that run reliably in real-world environments. Own AI features end-to-end: Take responsibility from idea → prototype → evaluation → production, with a strong focus on quality, reliability, and impact.

Build robust RAG pipelines: Implement retrieval systems using embeddings, vector databases, and structured data to ensure grounded, high-quality outputs. Develop intelligent patient-facing features: Create systems that turn unstructured patient data into personalized insights and health reports.

Drive evaluation and quality: Build and iterate on evaluation frameworks for LLM outputs, retrieval quality, and agent performance. Collaborate cross-functionally: Work closely with product, data, and domain experts to translate real healthcare problems into effective AI solutions.

Your profile Bachelor's or Master's degree in Computer Science, Data Science, or a related field Strong experience building LLM-based applications in production Excellent Python skills Hands‑on experience with: RAG systems, embeddings, and vector databases Prompt engineering and structured outputs At least one major LLM framework (e.g.

LangChain, LangGraph, LlamaIndex) Experience with agent-based systems (e.g.

Autogen, CrewAI, or similar) Solid engineering fundamentals: clean code, testing, CI/CD, Docker Experience with LLM evaluation or search quality is a strong plus Familiarity with AWS, GCP, or Azure You are execution-focused and pragmatic — you ship and iterate quickly You’re comfortable working in ambiguity and fast-paced environments Why us?