Job Description

Job Summary

Builds the data and knowledge foundation for grounded, high-quality AI agents. Owns data pipelines, embeddings, vector stores, and RAG components on Google Cloud, extracting and normalizing data from Intel's enterprise sources for AI consumption.

Key Responsibilities

• Design and implement data ingestion, transformation, and embedding pipelines.
• Extract and normalize data from Databricks, ServiceNow, Snowflake, OneDrive, Adobe, and PDFs.
• Build RAG pipelines using Vertex AI Search, BigQuery, AlloyDB, and Vector Search.
• Optimize retrieval quality, chunking strategies, and prompt grounding.
• Ensure data privacy, PII controls, and access governance; monitor pipeline health and cost.

Skill Requirements

• Strong data engineering with GenAI/RAG experience.
• Hands-on BigQuery, Vertex AI Search, AlloyDB/Cloud SQL, Dataproc/Dataflow.
• Proficient in Python and SQL; embeddings and semantic search.
• Experience integrating enterprise data sources (Databricks, ServiceNow, Snowflake).

Other Requirements

• Knowledge graphs, data privacy/DLP, IAM.
• Adobe systems and unstructured/PDF data extraction.
• Pipeline orchestration and observability.
• 6+ years data engineering with 2+ years GenAI/RAG.
• Google Cloud Data Engineer certification preferred.
• Offshore (India), aligned to overlap with US stakeholders as needed.