Forward Deployed Engineer III, Google Cloud Consulting (German)

Genel Nitelikler ve İş Tanımı

## Minimum qualifications: - Bachelor’s degree or equivalent practical experience. - 2 years of experience in designing, building, and deploying NLP models and Generative AI agents. - Experience implementing DevOps and MLOps pipelines. - Experience in building generative AI solutions in a customer-facing role. - Experience in ML infrastructure (e.g., model deployment, model evaluation, data processing, and debugging) and coding in Python. - Ability to communicate in German fluently to support client relationship management in this region. ## Preferred qualifications: - Master’s or PhD in AI, Computer Science, or a related technical field. - Experience implementing multi-agent systems using frameworks (e.g., LangGraph, CrewAI, or ’s ADK) and complex patterns like ReAct, self-reflection, and hierarchical delegation. - Knowledge of Large Language Model ("LLM-native") metrics (tokens/sec, cost-per-request) and techniques for optimizing state management and granular tracing. - Proven ability to implement secure agentic workflows incorporating MCP, tool-calling, and OAuth-based authentication. - Ability to communicate in French, Spanish, Italian or other European languages fluently to support client relationship management in this region. ## Responsibilities - Serve as the primary developer for complex AI applications, transitioning from rapid prototypes to production-grade agentic workflows (e.g., multi-agent systems, Model Context Protocol (MCP) servers) that generate measurable Return on Investment (ROI). - Architect and code the connective tissue between ’s AI products and customer's live infrastructure, including APIs, legacy data silos, and security perimeters. - Build high-performance evaluation (Eval) pipelines and observability frameworks to ensure agentic systems meet precise requirements for accuracy, safety, and latency. - Identify repeatable field patterns and technical "friction points" in ’s AI stack, converting them into reusable modules or formal product feature requests for the Engineering teams.