Tech Stack

Description

You will shape how AI systems retrieve, structure, and leverage context at scale, owning end-to-end delivery of unstructured AI systems from prototype to production. Build full-stack systems for processing large volumes of documents (PDFs, contracts, reports) across enterprise environments.

Requirements

• Strong proficiency in Python (data processing, API development, integrations)
• Hands-on work with LLM-based and AI-driven enrichment models
• Proven ability to deliver production-grade systems using Big Data frameworks (e.g., Spark)
• Solid understanding of data pipelines, microservice architecture, and API design
• Experience ingesting data from third-party enterprise sources (SharePoint, Salesforce)

Responsibilities

• Own end-to-end technical delivery of Unstructured AI systems from prototype to production
• Build and scale full-stack systems for ingesting, processing, and enriching unstructured content
• Write production-grade backend code (Python, FastAPI)
• Build and deploy document-processing systems for large-scale unstructured data
• Integrate data from diverse enterprise sources (SharePoint, Salesforce, internal APIs)