You will lead a team of Applied AI Engineers to architect and maintain systems for measuring, verifying, and enforcing data quality across billions of records. This involves building verification pipelines, LLM-based validators, and release gates to ensure high-quality data reaches customers.
You will lead the design, development, and operation of backend services, RESTful APIs, and AI/LLM systems while managing two engineering pods. This role is 80% hands-on architecture and engineering, focusing on building scalable, reliable, and observable production systems.
You will architect the transformation and warehouse layer to process billions of records while designing production infrastructure for LLM-based extraction and enrichment. You are responsible for building eval harnesses, managing token budgets, and ensuring data quality through robust orchestration and observability patterns.
You will build and maintain scalable data pipelines that integrate LLMs for extraction, enrichment, and validation of billions of records. You are responsible for ensuring data reliability, cost management, and observability across the entire data platform.
You will architect and maintain resilient, high-scale data extraction pipelines using a mix of deterministic parsers and LLM-based systems. You will also own the end-to-end ETL infrastructure, ensuring data quality, observability, and performance across the platform.
