About this role
Senior AI Engineer - Agentic AI Evaluation at Resaro AI. Location: Munich, Bavaria, Germany. Role: owning evaluation, evaluating agents, designing tests Requirements: 5+ years production software engineering in Python, deep experience with agentic AI, measurement and evaluation of multi-step agents, strong engineering judgment and communication. Category: Software Development Seniority: Senior Level Tools: Python, Parquet, Iceberg, DuckDB, Nuclio, Kubernetes, Helm, CUDA, GPU, GAIA, τ²-bench, OSWorld, SWE-bench Verified, WebArena Commitment: Full Time Workplace: Onsite Languages: English