Google Cloud Platform Architect

• System Architecture: Architect the end-to-end design of a scalable, GenAI-powered remediation platform on Google Cloud Platform. Design ingestion patterns to normalize data from Mainframe (z/OS), AS400, and Splunk into a Common Information Model (CIM). BigQuery Data Foundation: Establish BigQuery as the centralized source of truth. Design and implement efficient ELT/ETL pipelines and utilize BigQuery Vector Search for RAG (Retrieval-Augmented Generation) workloads. Human-in-the-Loop (HITL) Workflow: Engineer the critical workflow for "Low Confidence" incident handling. Ensure seamless integration between AI-generated hypotheses and expert analyst resolution, creating closed-loop feedback mechanisms that improve model accuracy over time. Governance & Compliance: Implement row-level security (RLS) and data masking to meet Healthcare regulatory requirements while providing LLMs the context needed for inference. Model Lifecycle & MLOps: Oversee the LLM and MLOps lifecycle, managing retraining triggers based on verified analyst resolutions, model evaluation, and performance monitoring.

Cloud Platform: Expert-level proficiency in Google Cloud Platform (Vertex AI, BigQuery, Dataflow, Pub/Sub, Cloud Run, Cloud Functions). GenAI & RAG: Deep practical experience with RAG architectures, embedding models, and vector database management (specifically within the BigQuery ecosystem). Legacy Integration: Strong background in connecting legacy enterprise infrastructure (Mainframe/AS400) to modern cloud data pipelines. Engineering Practices: Proficiency in Python/SQL, PYSPARK and infrastructure-as-code (Terraform) for reproducible, automated deployment. Communication: Ability to serve as a technical bridge, explaining complex AI trade-offs to stakeholders while providing clear guidance to engineering teams