About the role
Deeploi in München (Germany) seeks an experienced AI/ML Engineer to design and build LLM-powered agents automating support workflows across Zendesk, Intercom, and internal systems. You will own prompt engineering, tool-use design, and MLOps infrastructure to ensure production-quality agents with measurable impact.
Join a small, ambitious team in Berlin and Munich backed by top European VCs, with a competitive salary plus virtual share package (VSOP) and benefits like public transport tickets and
Design and build LLM-powered AI agents to automate support workflows across Zendesk, Intercom, and internal systems. Develop agents that understand requests, plan next steps, retrieve relevant context, take action, and elevate to human agents when needed. Own prompt engineering, tool-use design, and evaluation frameworks to ensure reliable, production-quality agent behavior. Build and maintain the MLOps infrastructure behind it (model serving, CI/CD, monitoring, safe rollouts). Track impact through KPIs such as resolution time, first-touch resolution, and automation rate. Integrate these systems with our existing TypeScript/Python stack, internal APIs, and knowledge bases. Work closely with Support, Product, and Engineering to identify the highest-impact automation opportunities. Share what you learn with the team and help other engineers apply LLM-driven automation effectively. 6+ years of experience in Software or Machine Learning Engineering. Proven track record deploying LLM/GenAI systems in production. Experience designing AI systems for scale in automation or decision support. Hands-on with LLM architecture: tool calling, RAG, orchestration, memory/context management, evaluation, guardrails. Strong MLOps and production AI infrastructure (deployment, CI/CD, monitoring, incident handling). Proficiency in Python and/or TypeScript/JavaScript. Excellent English (C1); German is a plus. Public transport ticket Urban Sports Club/EGYM Corporate Benefits VSOP