Generative AI engineer in multi-agent systems

Digitl is a young and innovative company in the fields of marketing and cloud technology. In a collaborative and cross-functional environment, we develop new concepts to guide our customers from various industries into a digitally shaped future. Join us and contribute your own fresh and forward-looking ideas as a Generative AI Engineer to help shape Digitl's continued development. In this role, you will design and develop production-quality multi-agent systems on Google Cloud. You will architect and implement scalable agent networks using the Google Agent Development Kit, Vertex AI Agent Engine, and leading foundation models such as Gemini and Claude.

• Design and implement production-ready multi-agent systems with clearly defined strategies for planning, routing, memory, and tool integration
• Design robust communication architectures between agents and develop modular components for extensible multi-agent systems
• Implement structured outputs, schema validation, and function calling
• Define guardrails, fallback strategies, and mechanisms to mitigate hallucinations
• Design evaluation pipelines for quality, latency, and cost
• Work with Gemini, Claude, and open models via APIs
• Implement advanced prompt engineering and system instruction design
• Optimize model usage in terms of cost, latency, and reliability
• Build and maintain RAG pipelines using vector databases
• Implement observability, tracing, and monitoring for LLM-based systems
• Architect cloud-native AI systems on Google Cloud
• Use Vertex AI, Agent Engine, Model Garden, and related services
• Deploy services using Vertex AI Agent Engine, Cloud Run, GKE, or serverless architectures
• Implement CI/CD pipelines and infrastructure as code
• Ensure a secure architecture with IAM, service accounts, and data governance
• Work closely with the Cloud, Ad Technology, and Digital Analytics teams
• Create technical documentation as well as internal training and knowledge materials
• Lead technical workshops and mentor engineers in agent system design

• More than 3 years of experience in software engineering, ML engineering, or backend systems
• Proven experience building and deploying LLM-based systems in production
• Hands-on experience with the Google Agent Development Kit, LangChain, LangGraph, or comparable agent frameworks
• Strong Python skills and sound software architecture practices
• In-depth understanding of LLMOps, including versioning, evaluation, monitoring, and cost control
• Experience with RAG architectures and vector databases
• Comprehensive knowledge of Google Cloud, especially Vertex AI and cloud-native deployment patterns
• Experience designing secure and scalable distributed systems
• Hands-on experience with Google Cloud authentication, including OAuth 2.0, service accounts, and IAM
• Excellent communication skills in English and German

• You have a place in the best co-working spaces in Düsseldorf, Zurich, Barcelona, or Hamburg
• All our processes are designed for remote work. You decide whether you prefer to work from home or spend your day in one of our offices
• We provide a standard setup for your remote working environment
• If you have a dog, you can bring it to any of our offices
• As a highly specialized technology partner, we support your development with certifications, conference attendance, and training