Job Description
Define and evolve the end-to-end architecture for Unstructured’s data transformation and retrieval platform. Build and scale distributed systems that process massive volumes of unstructured data across diverse formats and sources. Serve as the company-wide authority on Kubernetes orchestration, cluster design, performance tuning, and reliability. Lead Python architecture and best practices—ensuring performance, modularity, and maintainability across services. Design and optimize Postgres schemas, queries, and indexing strategies to support large-scale metadata and retrieval pipelines. Mentor senior engineers through design reviews and code guidance, raising the bar for technical excellence across the org. Partner with the infrastructure and product teams to translate research prototypes into production-grade systems. Evaluate emerging technologies and open-source tools in LLM infrastructure, retrieval, and orchestration—deciding where and how to integrate them.
About Unstructured
Unstructured is building the core infrastructure layer that powers enterprise-grade retrieval-augmented generation and unstructured data transformation.