LLM Deployment Engineer

About the role

Destinus is looking for an LLM Deployment Engineer in Zurich to drive the adoption of AI-powered automation across the organization. You will deploy and scale large language models to streamline business processes and support engineering R&D, working at the intersection of machine learning, software infrastructure engineering and enterprise systems.

Key responsibilities

• Deploy and maintain open-weight LLMs on cloud and local clusters
• Scale deployments so they can serve a large number of internal users
• Stay up to date with new model releases
• Connect LLMs to specific use cases so users can automate their daily work
• Analyze the effectiveness of models on automation tasks
• Embed security and privacy into the automation pipeline to protect sensitive content

Required profile

• 3+ years of professional experience in software engineering
• Experience with LLM APIs, both open-weight and proprietary
• Familiarity with LLM applications, including tools, retrieval-augmented generation (RAG) and routing
• Understanding of security and privacy in enterprise environments
• Strong problem-solving skills and ability to collaborate across technical and non-technical teams

Nice to have

• Knowledge of Model Context Protocol (MCP) or similar interoperability standards
• Experience with AI governance, observability or operational monitoring
• Cloud platform knowledge (AWS, GCP or Azure) and high-performance computing environments (Kubernetes, SLURM)
• Experience evaluating ML models