Member of Technical Staff (AI Inference Engineer)

Perplexity · London, United Kingdom · Full-time

Team: AI Research & Systems

Posted: 2026-04-13

Estimated pay (not employer-provided): USD 147000 – USD 299000 per year

The AI Inference Engineer is responsible for developing and optimizing high-performance inference infrastructure to support transformer-based models at scale. The role requires building Rust-based serving runtimes, migrating GPU kernels to CuTe DSL, and ensuring system reliability through performance profiling and observability. Candidates must have at least three years of professional experience in ML inference or high-performance systems, with deep expertise in GPU programming and LLM architectures.

Skills & tags: rust, python, cuda, cute dsl, llm architectures, gpu programming, distributed systems, performance optimization, pytorch, inference engineering

View and apply at the original posting

Postings belong to their employers; this page links to the source.

JOB DETAILS

Job details