Work directly with customers to design, deploy, and integrate end-to-end AI evaluation pipelines. Curate data, define annotation schemes, set up LLM-based judges, run initial experiments, produce actionable results, and translate technical systems into practical workflows for users.

Lead a 10-15 person backend team to design, build, and scale APIs, async workers, and cloud-native infrastructure on Google Cloud. Drive architecture, performance, reliability, and collaborate with DevOps, product, and design to ship production-grade features.