Nota AI
Senior Quantization Research Engineer
Seoul, South KoreaPosted 1 day ago
What you'd do
- Research and develop PTQ,QAT,and model compression algorithms for production deployment
- Design quantization strategies tailored to target model architectures and hardware constraints
- Optimize generative AI models (LLMs,diffusion models) and CV models for on-device inference
What they want
- Degree in CS or EE: BS plus 5 years,MS plus 3 years,or PhD required
- Deep research or engineering experience in quantization,model compression,or deep learning optimization
- Strong command of PyTorch,ExecuTorch,and ONNX for model optimization workflows
Nice to have
- Published papers at NeurIPS,ICML,CVPR,or ICLR on quantization or compression topics
- Experience deploying quantization research into commercial products or services at scale
- Familiarity with LLM inference frameworks: vLLM,SGLang,or llama.cpp