Description

Architect and build a scalable, GenAI-powered remediation platform on Google Cloud Platform, integrating legacy systems with modern AI workflows.

This role is hybrid.

Responsibilities

• Design end-to-end architecture for data ingestion from Mainframe (z/OS), AS400, and Splunk into a Common Information Model.
• Establish BigQuery as the central data foundation, implementing efficient ELT/ETL pipelines and Vector Search for RAG workloads.
• Engineer Human-in-the-Loop workflows for low-confidence incident handling, creating closed-loop feedback mechanisms to improve model accuracy.
• Implement row-level security and data masking to meet Healthcare regulatory requirements while providing context for LLM inference.
• Manage the LLM and MLOps lifecycle, including retraining triggers, model evaluation, and performance monitoring.

Required Skills

• Expert proficiency in GCP services: Vertex AI, BigQuery, Dataflow, Pub/Sub, Cloud Run, and Cloud Functions.
• Deep practical experience with RAG architectures, embedding models, and vector database management within BigQuery.
• Strong background in connecting legacy enterprise infrastructure (Mainframe/AS400) to modern cloud data pipelines.
• Proficiency in Python, SQL, and PySpark for data engineering tasks.
• Experience with Infrastructure-as-Code, specifically Terraform, for automated deployment.
• 6+ years of relevant engineering experience.

Preferred Skills

• Ability to serve as a technical bridge, explaining complex AI trade-offs to stakeholders.
• Experience with Healthcare regulatory compliance in cloud environments.

Key Skills

Education

Any Gradute