Job Description:
The position involves building and scaling AI-driven document systems. This includes working on production services that ingest, manage, retrieve, and reason over large document collections with a focus on PDFs and LLM-powered retrieval + analysis (RAG). The role requires owning critical components end-to-end from document pipelines to evaluation, latency, and cost.
Responsibilities:
* Designing, building, and operating production-grade Python services powering document & AI workflows.
* Owning document ingestion & management pipelines including reliability & scalability.
* Implementing RAG/semantic search systems combining LLMs with document retrieval.
,
The ideal candidate will have advanced Python skills in backend development with experience designing complex data processing workflows. They will also possess strong knowledge of natural language processing principles as well as hands-on experience working with embeddings vector databases.
,