👋 About the Team
The Core Research team researches and develops the core technologies for NetsPresso's main modules.
At NetsPresso, we convert deep learning models from various framework IRs (Intermediate Representations) into a unified IR. We then apply lightweight optimization techniques such as Graph Optimization, Quantization, and Compression to accelerate them for specific hardware (HW) characteristics.
We focus on optimizing Computer Vision and the latest Generative AI models for acceleration on target HW. We are dedicated to enhancing the performance and versatility of NetsPresso by developing new lightweighting methods and technologies compatible with a wide range of devices, from edge devices to data center servers.
📌 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.
📙Achievements & Relevant Materials
✅ Key Responsibilities
- Research and commercialization of Quantization technology
- Researching Post-Training Quantization (PTQ) algorithms and Quantization-Aware Training (QAT) techniques for various deep learning models
- Developing a framework for applying quantization techniques tailored to model and HW characteristics
- Application to Generative AI (LLM, VLM, Diffusion, etc.), Computer Vision (Classification, Detection, Segmentation, etc.), and other diverse AI models
- Optimization and conversion of on-device AI models
- Model optimization and conversion using various frameworks such as ExecuTorch, ONNX, and TensorRT
- Analyzing and resolving accuracy issues caused by quantization
✅ Requirements
- Master's degree or higher in Computer Science, Electrical Engineering, or a related field
- (Or) A Bachelor's degree with at least 2 years of relevant experience
- Ability to learn quickly and apply knowledge to development, even with limited prior experience in quantization
- Experience in optimizing PyTorch-based deep learning models
- No restrictions on international travel
✅ Pluses
- R&D experience in quantization, model compression, or kernel optimization
- Experience in model optimization using libraries such as ExecuTorch, ONNX, TensorRT, or AIMET
- Experience porting low-bit models to embedded devices
- Experience publishing research papers related to deep learning model optimization
✅ Hiring Process
- Document Screening → Technical Assignment → 1st Interview → 2nd Interview
(Additional assignments may be given, or the process may be simplified based on individual experience.)
🤓 A Message from the Team
We’re looking for someone who is passionate about new technology and turning ideas into working solutions. This role is more than just research—you’ll be developing original quantization methods that directly power NetsPresso services. Because our modules are deeply interconnected, we value active communication and a proactive mindset. If you enjoy diving deep into complex technical problems and growing alongside a collaborative team, you’ll thrive here.
Please Check Before Applying! 👀
- This job posting is open continuously, and it may close early upon completion of the hiring process.
- Please ensure that sensitive personal information, such as salary details, ID number etc., is not included in your resume.
- 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.
Veterans and individuals with disabilities will receive preferential treatment in accordance with relevant regulations.
🔎 Helpful materials
👋 About the Team
The Core Research team researches and develops the core technologies for NetsPresso's main modules.
At NetsPresso, we convert deep learning models from various framework IRs (Intermediate Representations) into a unified IR. We then apply lightweight optimization techniques such as Graph Optimization, Quantization, and Compression to accelerate them for specific hardware (HW) characteristics.
We focus on optimizing Computer Vision and the latest Generative AI models for acceleration on target HW. We are dedicated to enhancing the performance and versatility of NetsPresso by developing new lightweighting methods and technologies compatible with a wide range of devices, from edge devices to data center servers.
📌 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.
📙Achievements & Relevant Materials
✅ Key Responsibilities
- Research and commercialization of Quantization technology
- Researching Post-Training Quantization (PTQ) algorithms and Quantization-Aware Training (QAT) techniques for various deep learning models
- Developing a framework for applying quantization techniques tailored to model and HW characteristics
- Application to Generative AI (LLM, VLM, Diffusion, etc.), Computer Vision (Classification, Detection, Segmentation, etc.), and other diverse AI models
- Optimization and conversion of on-device AI models
- Model optimization and conversion using various frameworks such as ExecuTorch, ONNX, and TensorRT
- Analyzing and resolving accuracy issues caused by quantization
✅ Requirements
- Master's degree or higher in Computer Science, Electrical Engineering, or a related field
- (Or) A Bachelor's degree with at least 2 years of relevant experience
- Ability to learn quickly and apply knowledge to development, even with limited prior experience in quantization
- Experience in optimizing PyTorch-based deep learning models
- No restrictions on international travel
✅ Pluses
- R&D experience in quantization, model compression, or kernel optimization
- Experience in model optimization using libraries such as ExecuTorch, ONNX, TensorRT, or AIMET
- Experience porting low-bit models to embedded devices
- Experience publishing research papers related to deep learning model optimization
✅ Hiring Process
- Document Screening → Technical Assignment → 1st Interview → 2nd Interview
(Additional assignments may be given, or the process may be simplified based on individual experience.)
🤓 A Message from the Team
We’re looking for someone who is passionate about new technology and turning ideas into working solutions. This role is more than just research—you’ll be developing original quantization methods that directly power NetsPresso services. Because our modules are deeply interconnected, we value active communication and a proactive mindset. If you enjoy diving deep into complex technical problems and growing alongside a collaborative team, you’ll thrive here.
Please Check Before Applying! 👀
- This job posting is open continuously, and it may close early upon completion of the hiring process.
- Please ensure that sensitive personal information, such as salary details, ID number etc., is not included in your resume.
- 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.
Veterans and individuals with disabilities will receive preferential treatment in accordance with relevant regulations.
🔎 Helpful materials