Description

You build the connectors, knowledge bases, and retrieval layers that ground generative AI applications in approved enterprise content, enforcing data classification and access boundaries.

This role is remote.

Responsibilities

• Build and configure connectors and ingestion pipelines for SharePoint Online, Exchange/Outlook, OneDrive, and Teams.
• Design and maintain knowledge base structures using Amazon Bedrock Knowledge Bases and Amazon OpenSearch, managing chunking, metadata, and indexing strategies.
• Integrate structured data sources such as Amazon Athena, Redshift, RDS, and S3 for retrieval and analysis.
• Implement document-level and user-level access enforcement to respect data classification, PHI/PII boundaries, and least-privilege principles.
• Build a retrieval-evaluation framework to iteratively improve relevance, accuracy, and grounding/citation quality.

Required Skills

• 5+ years of experience with search, retrieval, or knowledge-base systems and data pipelines.
• Hands-on experience with embeddings, vector stores, and RAG retrieval patterns.
• Strong understanding of data permissions, document-level/user-level access control, and governance (including PHI/PII).
• Experience with data ingestion, connectors, indexing, and content preparation, ideally including Microsoft 365 sources.
• Familiarity with AWS data and AI services (Amazon Bedrock Knowledge Bases, OpenSearch, Athena/Redshift/RDS/S3) and core AWS fundamentals.
• Ability to document data flows, indexing decisions, and retrieval configurations for handover.

Preferred Skills

• Experience with Amazon OpenSearch, Kendra, Amazon Q Business, or comparable enterprise search platforms.
• Background in data engineering or information retrieval.

Key Skills

Education

Any Graduate