Engineer Evals Agent Quality Jobs in San Francisco, CA

Partner with engineers across the product to instrument quality and close the loop from signal to fix.

We're looking for an Agent Experience Engineer to own how AI models and agents discover and use AgentMail.

About the Role The Enterprise Agent Evals & Efficiency team makes Perplexity's agents better at completing real work across enterprise

and eval infrastructure we use to monitor agent behavior, debug issues, and raise quality over time Help to scale multi-tenant systems that keep

own Hercules' online evals and offline evals.

In saying this, you will work with an engineering counterpart to work on complex implementation Evals.

You'll build evals and use production traces to improve how the harness translates company knowledge into reliable agent behavior.

As an Engineering Manager for AI Platform, you will lead a team of engineers building the horizontal systems that make Harvey’s AI products higher quality

means to balance craft, ownership, and speed Familiarity with tools that power today's AI agents: eval frameworks, agent tooling, RAG pipelines,

Coach and develop engineers through career growth, feedback, and technical leadership, building a culture of ownership and high-quality execution.

means to balance craft, ownership, and speed Familiarity with tools that power today's AI agents: eval frameworks, agent tooling, RAG pipelines,

Perplexity serves tens of millions of users daily with reliable, high-quality answers grounded in an LLM-first search engine and specialized data sources.

Build, maintain, and own Hercules' AI coding agent Build, maintain, and own Hercules' online evals and offline evals

They should have peace of mind, with trustworthy consent and authorization, when agents shop on their behalf.