Build pipelines for structured and unstructured data including docs, PDFs, emails, and logs
Design and implement backend services that support LLM workflows: retrieval, indexing, embeddings, batch processing, and job queues
Own data quality end to end: validation, deduping, lineage, versioning, and reproducible runs
Create observability for pipelines and LLM systems to surface issues quickly and identify root causes clearly

Requirements

Solid backend engineering skills in Python
Strong understanding of data systems: SQL, schemas, indexing, partitioning, and performance tradeoffs
Comfort with statistical concepts relevant to model evaluation, or experience interpreting metrics and distributions

Benefits

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

PythonSQLdata validationdedupingdata lineageversioningreproducible runsretrievalindexingbatch processing