✨ The Role in One Sentence

SEMRON is seeking an ML Quantization Engineer to build a scalable inference framework for AI hardware on Edge devices.

📋 What You'll Likely Do

• 40%: Develop and maintain an inference framework tightly tuned for SEMRON hardware.

• 30%: Collaborate with ML, compiler, and hardware teams to refine quantization algorithms.

• 30%: Apply and innovate on quantization methods like AdaRound, BRECQ, GPTQ, and QuaRot.

🧑‍💻 Profiles Doing This Job

• High Priority: Solid skills in PyTorch and experience with torch.FX.

• High Priority: Understanding of quantization research and hands-on experience.

📈 How This Role Will Look on Your CV

• Built and maintained an inference framework for AI hardware, contributing to open-source projects.