Architect enterprise-scale, production-ready Data-to-AI platforms, advanced Retrieval-Augmented Generation (RAG) pipelines, semantic knowledge graphs, and vector databases using Vertex AI Vector Search to support scalable generative AI applications. Lead end-to-end implementation of Google Cloud data platforms using BigQuery, Dataflow, Pub/Sub, and AlloyDB, building high-throughput batch and streaming pipelines that optimize complex query performance.
Design, build, and deploy autonomous AI agents and multi-agent coordination systems by leveraging the Vertex AI Agent Ecosystem, Reasoning Engine, and the comprehensive Gemini foundation model family. Implement agentic reasoning loops, memory systems, tool and API integrations, and robust AgentOps frameworks for continuous monitoring, tracing, evaluation, fine-tuning, latency optimization, cost control, and safety compliance.
Advise executive stakeholders on generative AI transformation, lead technical scoping and rapid prototyping workshops, and mentor engineering teams in modern Google Cloud Data and AI system architectures.
Job description provided by Google.
View the original posting
