👋 About the Team
The NetsPresso Platform team designs and implements the core platforms and software that transform Nota AI's AI model compression and optimization technologies into real products for users.
The team consists of Model Representation, Quantization, Graph Optimization, Model Engineering, and SW Engineering parts. Among these, the Quantization part focuses on researching quantization—a core optimization technology of NetsPresso—and integrating our proprietary techniques into products to accelerate deep learning model inference across various hardware.
- we research algorithms that minimize accuracy degradation caused by quantization.
- we support quantization tailored to the constraints of diverse hardware and backend.
- we convert models into formats that enable acceleration on actual hardware.
📌 What You’ll Do at This Position
You will research and commercialize the quantization technology in NetsPresso. You will research the latest quantization algorithms and design Nota's unique quantization techniques, optimizing them for the characteristics of various models and HW. You will get to experience various optimization technologies for on-device AI and work with the latest models.
✅ Key Responsibilities
- Research and commercialization of Quantization technology
- Research and develop next-generation Post-Training Quantization (PTQ), Quantization-Aware Training (QAT), and Compression algorithms
- Establish quantization strategies and design frameworks considering model architecture and target HW characteristics
- Research optimization methodologies for Generative AI (LLM, VLM, Diffusion, etc.), Computer Vision (Classification, Detection, Segmentation, etc.), and diverse AI models
- Secure technical leadership through publications and patent filings
- Optimization of on-device AI models
- Design and enhance quantization pipelines for deployment across various on-device hardware
- Drive AI model optimization projects
- Analyze root causes of accuracy degradation from quantization and establish systematic solutions
✅ Requirements
- Master's degree or higher in Computer Science, Electrical Engineering, or a related field
- R&D experience in quantization, model compression, or deep learning optimization
- Understanding of PyTorch / Executorch / ONNX-based deep learning model optimization
- No disqualifications for overseas travel
✅ Pluses
- Publications at top-tier conferences (NeurIPS, ICML, CVPR, ICLR, etc.) in quantization, model compression, or kernel optimization
- Experience commercializing research results and applying them to production services
- Advanced experience with optimization libraries such as ExecuTorch, ONNX, TensorRT, or AIMET
- Experience porting low-bit models to embedded devices and performance tuning
- Experience with LLM Inference Framework such as vLLM, SGLang, llama.cpp
- Contribution to or maintenance of open-source projects
- Ph.D. degree holder
✅ Hiring Process
- Document Screening → 1st Interview → Assignment → 2nd Interview → 3rd Interview → Offer → Hire
(Additional assignments may be included during the process.)
🤓 A Message from the Team
We value people who are genuinely curious about emerging technologies and have the drive to turn ideas into real-world solutions.
This role goes beyond research. You will develop proprietary quantization technologies that are directly integrated into the NetsPresso platform and used in real-world products.
Because our technologies are built on closely connected modules, we place a strong emphasis on open communication, collaboration, and a proactive approach to problem-solving.
If you enjoy diving deep into complex technical challenges, growing alongside talented teammates, and building technologies that make a real impact, we believe you'll find meaningful opportunities to achieve great results with our team.
Please Check Before Applying! 👀
- This job posting is open continuously, and it may close early upon completion of the hiring process.
- Resumes that include sensitive personal information, such as salary details, may be excluded from the review process.
- Providing false information in the submitted materials may result in the cancellation of the application.
- Please be aware that references will be checked before finalizing the hiring decision.
- Compensation will be discussed separately upon successful completion of the final interview.
- There will be a probationary period after joining, and there will be no discrimination in the treatment during this period.
- To support the employment of persons with disabilities, you may optionally submit a copy of your disability registration certificate under “Additional Documents,” if administrative verification is required. Submission is optional and does not affect the evaluation process.
- Veterans and individuals with disabilities will receive preferential treatment in accordance with relevant regulations.
🔎 Helpful materials
