Remote job
Data Engineer
Job details
About this role
Role overview
A data engineering role building the ingestion and evaluation infrastructure behind autonomous AI agents that serve customer-facing support workflows. The work spans pipeline design, dataset curation, and feedback systems that keep agent behavior accurate, fresh, and auditable across many source systems.
Responsibilities
- Design and own ingestion pipelines for helpdesk tickets, knowledge-base content, CRM data, and product documentation - Build evaluation infrastructure that powers a multi-dimension accuracy methodology and a self-evaluation layer - Instrument data quality monitoring, freshness SLAs, and regression detection across customer deployments - Partner with ML and forward-deployed engineers to keep agent grounding current and auditable
Requirements
- 3+ years of professional experience in data engineering - Strong proficiency in Python and SQL - Production experience with relational databases such as Postgres or an equivalent, plus event-driven or streaming systems - Familiarity with retrieval pipelines — chunking, embeddings, vector stores — or a clear willingness to ramp up quickly - A bias for shipping: caring about data actually making it to production, not just pipelines that compile and run