Tech Lead, ML Inference Performance

Screened

Greater London

Posted 1 week ago

About the role

DeepMind in London seeks a Tech Lead for Gemini Inference Performance to guide a team of performance engineers and drive optimization across ML frameworks and hardware accelerators.

You will leverage transformer and Mixture-of-Experts concepts to improve latency and memory efficiency while collaborating with research teams on deployment trade-offs. A strong leadership track record is essential.

#J-18808-Ljbffr

About this listing

Screened by Joboru

This role passed our automated spam and quality filters and was active in our feed when last checked. Joboru is an aggregator — here is how we screen listings. If anything looks off, tell us.