Solvd Inc. is seeking a Senior Data Engineer to build four source connectors and an ingestion pipeline that transforms raw knowledge content into a governed, permission-tagged corpus in Amazon S3 and Amazon Bedrock Knowledge Bases. The engineer will own the ingestion workstream end to end within an architecture established by the Solution Architect, and pair with the retrieval engineer so deliverables are shared. The goal is to ingest every in-scope item from four source systems while preserving metadata, permissions, and lineage, support a client-tunable synchronization schedule, and propagate retirements on the next run. The position involves creating connectors for iKNOW, SharePoint, OneDrive, Teams, and Sitecore, and implementing ingestion, content processing, indexing, retirement handling, monitoring, and operational documentation. The engineer will also produce inventory extracts for content disposition reviews and re-baselining, address API throttling and pipeline failures, and pair with client IT during weeks 7–10 to support their ability to operate and extend the pipelines after transition.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed