Software Engineer (Quantization Engineer) at FuriosaAI - ScoutJobs - The AI-curated global job board
Skip to content
F
Posted 8 hours ago

Software Engineer (Quantization Engineer)

FuriosaAISoftware Engineer (Quantization Engineer)

Requirements

Extensive PyTorch development experience, Commercial software development experience, 3+ years of professional experience

Skills

PyTorchLLM

About the role

Responsibilities

  • Develop Model Compression tools
  • Secure various quantized models and verify performance
  • Develop advanced compression algorithms based on verification results

Requirements

  • Extensive experience with PyTorch development
  • Experience in commercial software development
  • 3+ years of professional experience in a related field

Preferred Qualifications

  • Experience and knowledge in DevOps and MLOps
  • Experience using LLM inference tools such as vLLM or TensorRT-LLM
  • Knowledge and experience in Deep Learning Quantization
  • Experience working at companies related to Deep Learning acceleration

About the Company

FuriosaAI's Model Compression Part aims to solve the challenges of applying LLM quantization to real-world services by developing user-friendly tools that maximize NPU efficiency through hardware-specific optimization.

ScoutJobs Agent

Get matches like this delivered daily

Sign up free — we'll pull jobs that fit your CV from across the web and rank them for you.

Get started — it's free

Software Engineer (Quantization Engineer)

FuriosaAI · Seoul

Sign up to apply