Skip to content

Job · Perplexity AI

Member of Technical Staff (AI Inference Engineer)

EmployerPerplexity AI
LocationLondon
FunctionData & research
TypeFull-time
Posted13 Apr 2026

About the role

Perplexity AI seeks an AI Inference Engineer to build and optimize its internal inference engine. The role involves developing Rust-based serving runtimes, migrating GPU kernels to CuTe DSL, and supporting transformer models. Candidates need three years of experience in high-performance systems, deep learning frameworks, and GPU architecture.

Summary written by GAR, Octum’s cognitive engine, from the employer’s posting. The full description is on the employer’s site.

More roles at Perplexity AI

All Perplexity AI roles →

Collected by Octum from Perplexity AI’s careers site on 31 Oct 2026; Octum is not the employer and does not take applications. Spotted something wrong? Tell us.