What are the responsibilities and job description for the AI & Data SME position at Shrive Technologies?
Role Summary
Serves as the senior subject-matter expert bridging enterprise data engineering and AI grounding for the Agent Factory. Owns the strategy and design for extracting, normalizing, and grounding Intel enterprise data (Databricks, ServiceNow, Snowflake, OneDrive, Adobe, PDFs) for high-quality, reliable AI agent consumption, and advises on data architecture, RAG quality, and AI data governance.
Key Responsibilities
Define the enterprise data-to-AI strategy: ingestion, normalization, embeddings, vector stores, and RAG grounding for agents.
Architect and oversee data pipelines from source systems (Databricks, ServiceNow, Snowflake, OneDrive, Adobe, PDFs) into Google Cloud (BigQuery, Vertex AI Search, AlloyDB, Vector Search).
Own retrieval quality: chunking strategies, embedding models, hybrid search, and grounding accuracy for Finance/Marketing/HR agents.
Establish AI data governance: data privacy, PII controls, lineage, quality, and access management.
Advise architects and developers on data readiness, feature/knowledge design, and evaluation of grounded responses.
Guide model selection and cost/performance trade-offs for data-heavy agent workloads.
Act as a senior technical authority in stakeholder discussions with Intel and Google on data-track dependencies.
Mentor Data & AI Engineers and set standards for reusable data assets in the Intel Agent Library.
Mandatory (Must-Have) Skills
Deep enterprise data engineering: pipelines, ETL/ELT, data modelling, and data quality at scale.
Hands-on with Google Cloud data stack: BigQuery, Vertex AI Search, AlloyDB/Cloud SQL, Dataflow/Dataproc.
Strong RAG design: embeddings, vector databases, chunking, hybrid/semantic search, grounding evaluation.
Experience integrating enterprise sources (Databricks, ServiceNow, Snowflake, SharePoint/OneDrive).
Proficiency in Python and SQL; solid grasp of GenAI/LLM data patterns.
Strong data governance, privacy (PII/DLP), and security knowledge.
Preferred (Good-to-Have) Skills
Knowledge graphs and advanced retrieval (GraphRAG, corrective/self-RAG).
Snowflake / Databricks certifications; Google Professional Data Engineer.
Experience with AI evaluation frameworks and observability for data quality.
Prior high-tech / semiconductor domain exposure.
Experience & Certifications
9 12 years in data engineering / data architecture with recent GenAI/RAG delivery (Tier 5 6).
Google Professional Data Engineer / relevant cloud data certification preferred.
Onsite (USA), aligned to Intel hours and data-track stakeholder collaboration.
Serves as the senior subject-matter expert bridging enterprise data engineering and AI grounding for the Agent Factory. Owns the strategy and design for extracting, normalizing, and grounding Intel enterprise data (Databricks, ServiceNow, Snowflake, OneDrive, Adobe, PDFs) for high-quality, reliable AI agent consumption, and advises on data architecture, RAG quality, and AI data governance.
Key Responsibilities
Define the enterprise data-to-AI strategy: ingestion, normalization, embeddings, vector stores, and RAG grounding for agents.
Architect and oversee data pipelines from source systems (Databricks, ServiceNow, Snowflake, OneDrive, Adobe, PDFs) into Google Cloud (BigQuery, Vertex AI Search, AlloyDB, Vector Search).
Own retrieval quality: chunking strategies, embedding models, hybrid search, and grounding accuracy for Finance/Marketing/HR agents.
Establish AI data governance: data privacy, PII controls, lineage, quality, and access management.
Advise architects and developers on data readiness, feature/knowledge design, and evaluation of grounded responses.
Guide model selection and cost/performance trade-offs for data-heavy agent workloads.
Act as a senior technical authority in stakeholder discussions with Intel and Google on data-track dependencies.
Mentor Data & AI Engineers and set standards for reusable data assets in the Intel Agent Library.
Mandatory (Must-Have) Skills
Deep enterprise data engineering: pipelines, ETL/ELT, data modelling, and data quality at scale.
Hands-on with Google Cloud data stack: BigQuery, Vertex AI Search, AlloyDB/Cloud SQL, Dataflow/Dataproc.
Strong RAG design: embeddings, vector databases, chunking, hybrid/semantic search, grounding evaluation.
Experience integrating enterprise sources (Databricks, ServiceNow, Snowflake, SharePoint/OneDrive).
Proficiency in Python and SQL; solid grasp of GenAI/LLM data patterns.
Strong data governance, privacy (PII/DLP), and security knowledge.
Preferred (Good-to-Have) Skills
Knowledge graphs and advanced retrieval (GraphRAG, corrective/self-RAG).
Snowflake / Databricks certifications; Google Professional Data Engineer.
Experience with AI evaluation frameworks and observability for data quality.
Prior high-tech / semiconductor domain exposure.
Experience & Certifications
9 12 years in data engineering / data architecture with recent GenAI/RAG delivery (Tier 5 6).
Google Professional Data Engineer / relevant cloud data certification preferred.
Onsite (USA), aligned to Intel hours and data-track stakeholder collaboration.