AI Data Engineer
Core
Design, build, and maintain scalable ETL and data ingestion pipelines for an AI platform that applies Large Language Models to enterprise retrieval and document intelligence.
Role type
Senior IC AI Data Engineer
Builds
Scalable data pipelines, document understanding workflows, and ingestion solutions for the firm's AI platform
Domain
Alternative investment / AI and document intelligence
Deliverable
production ML models
Required skills
Python, ETL and data pipeline design, document processing and text extraction, data modeling and transformation, high-performance system design, data quality and observability
Preferred skills
RAG systems, chunking strategies, embeddings, vector stores
Technologies
Python, PDF, Office documents, OCR, APIs, object stores, databases, vector stores
Responsibilities
Design and build scalable ETL and data ingestion pipelines; Develop document understanding workflows including parsing, layout analysis, and OCR; Implement chunking, cleaning, and enrichment strategies for RAG systems; Engineer pipelines for correctness, throughput, and resilience; Establish data quality checks and observability; Partner with stakeholders to translate content requirements into production-ready solutions
Seniority
Senior, hands-on IC