Member of Technical Staff (Software Engineer, Enterprise Agent Evals & Efficiency)

The Enterprise Agent Evals & Efficiency team at Perplexity makes agents better at completing real enterprise work. This role involves building evaluation environments, owning evaluation infrastructure, analyzing failures, developing skills, improving model selection, and driving efficiency. The goal is to make enterprise work reliable and practical to automate.

5+ years of software engineering or ML engineering experience, strong system design, proficiency in Python/Go/Rust, hands-on experience with LLM-based applications, deep expertise in evaluation infrastructure, agent harnesses, test environments, or model selection, strong experimental judgment, and ability to lead cross-team initiatives.