Design, build, and own backend systems for high-throughput asynchronous GenAI workloads. Architect generation pipelines, inference orchestration, queuing, retries, worker orchestration, and performance/cost optimizations. Mentor engineers and set technical direction while writing production-ready code for scale and reliability.

Build and maintain high-performance backend services in Go, optimize PostgreSQL schemas and queries, design scalable distributed systems/microservices, apply systems-level knowledge (C/C++), troubleshoot and improve performance, participate in code reviews, and mentor junior engineers.