Member of Technical Staff Evaluation Infrastructure (LLM Inference)
In short
This role builds reliable, efficient evaluation infrastructure and internal tooling that runs evaluations at scale for an AI company. The focus is on maintaining evaluation signal quality and resolving performance bottlenecks across inference, fleet management, and asynchronous evaluation orchestration. It demands strong experience building, debugging, and optimizing large-scale distributed systems, with willingness to work across all layers of the stack.