Perplexity seeks engineer to train search agents that coordinate

A Perplexity Search job listing describes post-training and multi-agent research across models, harnesses and retrieval. Its publication year is unverified.

By · Published

Primary source: RuntimeWire original reporting

Why it matters

Multi-agent search has to improve answers while keeping latency and cost in check. Perplexity owning the model, harness and retrieval stack lets it train and measure all three together, while external benchmark evidence shows multi-agent systems still generally trail centralized retrieval.

Four small robots handle glowing search, database, document and sharing icons on a rocky ridge at sunset, beside a sign with a blue symbol.

A Perplexity Search job listing describes post-training and multi-agent research across models, harnesses and retrieval. Its publication year is unverified.

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Reader comments

Conversation for this story loads after sign-in.