Usiamo cookie tecnici e il registro anonimo delle visite di Zorky. Yandex Metrica (dati conservati su server in Russia) funziona solo con il tuo consenso. Non vendiamo mai dati. Ulteriori informazioni su cookie e statistiche.
Zorky è in modalità test: è tutto gratuito. Le offerte e le pagine delle aziende sono aperte a tutti; i link agli annunci e la tua selezione personale si aprono dopo la registrazione. Registrati →
← Tutte le offerte

Principal Architect, AI Inference Networking - NIXL and Dynamo

Principal5 g fa
Analisi del mercato
📊 Architecture: stipendi e domanda sul mercato
Stack
c++llmpythontritonvllm
Dettagli
English
C1, required
Education
PhD
Time zone
US
Mostra azienda e link
Gratis, dopo l'accesso.
Candidati
Apri l'azienda e il link qui sopra: la candidatura arriva direttamente nel sistema di selezione dell'azienda, senza intermediari.

Descrizione

Inference has become a networking problem. With disaggregated serving, where prefill runs on one set of GPUs, decode on another, and KV cache streams between them, performance depends on how fast you can move tensors between GPUs, across nodes, and in and out of storage. Performance is only half of it.

These deployments are elastic, so the data path needs dynamic APIs that let workers join and leave, connections form and tear down, and transfers reroute at runtime without stalling the pipeline. NIXL, […]'s open source Inference Xfer Library, is the layer that solves this, and it sits underneath […] Dynamo and a growing list of inference engines.

China is where some of the world's most demanding inference deployments are being built. We are hiring a senior architect to work directly with the platform teams building them, understanding what breaks at scale and turning that into upstream code and roadmap. You will work daily with core NIXL and Dynamo engineers in Israel and the US.

What you'll be doing:

  • Drive NIXL adoption in China, from the first architecture conversation through prototype and benchmark to production rollout and upstream contribution.
  • Profile customer inference stacks and fix what's costing throughput and TTFT: KV cache movement, memory registration, transfer scheduling.
  • Write NIXL backends and plugins, extend Dynamo integrations, and contribute optimizations upstream to NIXL and GPUDirect class data paths.
  • Help define the APIs that make the data path d
Descrizione completa, azienda e link per candidarti: dopo l'accesso. Accedi
I contatti del datore di lavoro (email/telefono/telegram) sono nascosti nell'anteprima pubblica.
Domanda urgente? Scrivi a @termdocs