Data / AI Engineer

Role overview Build and maintain the data foundations that make AI systems useful: turn source documents and system data into clean, searchable, well-organized records. The work spans ingestion, transformation, indexing, and the operational practices that keep retrieval reliable as data volumes grow.

Responsibilities - Manage data flows from raw documents and source systems through structured records, embeddings, and searchable stores. - Build and operate ETL/ELT pipelines for ingestion, metadata extraction, cleaning, normalization, and versioning. - Automate document chunking, embedding generation, and indexing at scale, keeping retrieval current and traceable to source material. - Design data architectures suited to changing volumes and make data quality and pipeline reliability measurable.

Requirements - Strong Python and/or TypeScript skills, solid SQL, and experience running production data pipelines. - Hands-on experience with relational, vector, and graph data stores, with judgment about which fits a given need. - Understanding of embeddings, semantic search, and retrieval, including how to tune result quality. - Careful handling of schema changes, repeatable reruns, backfills, costs, and failure modes.

Nice to have - Experience with AWS data services such as S3, Glue, Athena, or Bedrock Knowledge Bases, or equivalent tools. - Production experience with orchestration tools such as Airflow, Dagster, or Step Functions. - Work in a regulated field where data lineage and auditability are important.