About the Role: AI Lead Engineer:
* As our AI Lead Engineer, you will shape the design and delivery of the core intelligence layer behind Playbook's platform. From encoding complex regulatory rules into structured knowledge graphs to embedding them in next-gen LLM-based agents, you’ll architect and engineer solutions that are foundational to how our technology scales across industries.
* You’ll work end-to-end—from high-level system design to hands-on development—bridging deep AI architecture, product thinking, and enterprise integration. This role is ideal for someone ready to take ownership of technical direction, shape infrastructure from the ground up, and make real-time decisions that impact clients, models, and the product itself.
What You’ll Do:
* Architect and build the data and AI cloud-based infrastructure on AWS.
* Architect and build RAG pipelines that translate regulatory content (SOPs, policies, standards) into structured knowledge graphs and control logic leveraging AI.
* Develop real-time orchestration patterns to embed this logic into agent frameworks such as LangGraph, LangChain, CrewAI, and Autogen.
* Design scalable and modular components using vector databases, graph databases, semantic search, and transformer-based models.
* Own the decision-making process around system architecture, data pipelines, model integration, and retrieval strategies.
* Collaborate with enterprise clients and internal teams to translate abstract requirements into robust AI-driven compliance layers.
* Prototype, validate, and iterate quickly in an agile, feedback-driven environment.
* Influence and evolve our AI platform's technical strategy, working closely with product and engineering stakeholders.
Qualifications & Requirements:
Must-Haves:
* 5+ years of experience architecting and developing AI/ML systems in a production-grade environment, preferred in regulated settings.
* 5+ years of experience in cloud infrastructures on AWS, leveraging services such as Sagemaker, DynamoDB, DocumentDB, Textract, Kendra, Bedrock, Neptune, etc.
* Strong experience with LLMs, RAG pipelines, and knowledge graph design.
* Proficiency in modern AI/ML tooling: Python, JavaScript, LangGraph, LangChain, PyTorch, TensorFlow, OpenAI APIs, Hugging Face, etc.
* Deep understanding of retrieval systems, semantic embeddings, vector databases (e.g., FAISS, Weaviate, Pinecone), and orchestration frameworks.
* Ability to translate complex, domain-specific rules into formalized, machine-readable logic.
* Experience designing scalable containerized environments (Docker/Kubernetes).
* Clear, confident communicator who can collaborate cross-functionally and work directly with clients.
Bonus Points:
* Familiarity with tools for parsing and processing long-form documents (e.g., PDF mining, OCR, NLP pipelines).
* Background in knowledge representation, ontology engineering, or symbolic AI.
* Open-source contributions or published research in relevant fields.
* Exposure to agent orchestration frameworks (e.g., CrewAI, Autogen, Semantic Kernel).
Perks & Compensation:
* Competitive compensation with a meaningful equity stake — you won’t just build the future of agentic automation, you’ll own a piece of it.
* Founding-tier influence in a deep tech company with real enterprise traction and massive upside potential.
* Flexible work setup – we're based in Munich (Munich Urban Collab), but remote/hybrid arrangements are possible for the right person.
* Work alongside a high-caliber team of engineers, researchers, and operators obsessed with building AI that works in production.
* Opportunity to evolve into a key leadership position as we scale.
* Direct exposure to industry-defining challenges in Pharma, MedTech, and enterprise automation.
* Access to conferences, learning budgets, and the tools you need to stay ahead of the curve.
The Stack You’ll Touch:
* LangGraph, LangChain, CrewAI, Autogen, OpenAI APIs, LlamaIndex.
* Python, JavaScript, FastAPI, Neo4j, FAISS, Weaviate.
* AWS, Docker, Postgres, GitHub Copilot, Notion.
