03 ago
|
Tether.io
|
Italia
is seeking an AI research engineer to drive compression and efficient deployment for multimodal AI systems, including LLMs and VLMs.
La preghiamo di leggere attentamente le informazioni contenute in questo annuncio di lavoro per comprendere esattamente cosa ci si aspetta dai potenziali candidati.
You will focus on reducing model footprint and cost while preserving accuracy across edge devices, using quantization, distillation, and pruning.
You will build robust pipelines, measure performance, and publish findings. xlwpduy
A PhD or strong publications and PyTorch expertise are highly valued, with a global remote work setup.
#J-18808-Ljbffr
📌 AI Research Engineer: Multimodal Quantization & Efficiency (Italia)
🏢 Tether.io
📍 Italia