L’offerta in breve

Axelera AI: Senior AI Application Engineer - LLM & VLM Enablement. Lavoro da remoto nell’UE, aperto a candidati in Italia. Livello: senior. Contratto: Full-time. Tecnologie indicate: Python, PyTorch.

Responsabilità e requisiti sono riportati nel riepilogo editoriale qui sotto, nella lingua disponibile. Verifica i dettagli nell’annuncio dell’azienda prima di candidarti.

Sul ruolo

Axelera AI is hiring a Senior AI Application Engineer for its Model Enablement team. The role focuses on bringing large language and vision-language models to the Metis and Europa AI platforms, from evaluating new architectures to shipping supported features in the Voyager SDK. You’ll build model-side PyTorch references and contracts, integrate prefill, decoding, KV-cache management and multimodal inputs, and work with compiler and runtime teams to make models run effectively on the hardware.

You’ll also measure accuracy and performance, improve the LLM/VLM bring-up platform, and help shape SDK support for generative AI, agents and speech on edge devices. The role calls for at least five years of software engineering experience, including two years in ML inference, systems or tooling, plus practical transformer and quantization knowledge. Axelera offers fully remote work from European countries, including.

Highlights

Develop and ship LLM/VLM support for Metis and Europa accelerators.
Integrate model serving features into the Voyager SDK.
Work across PyTorch, quantization, compiler, runtime and hardware profiling.
Remote from any European country, including the UK; Italy and Belgium are priority locations.

Questo recap è un riassunto editoriale di dataskew, non il testo dell'azienda.