[NetsPresso] Quantization Research Engineer
Job GroupR&D
Experience LevelExperienced 2 years or more
Job TypesFull-time
Locations대한민국 서울특별시 강남구 테헤란로 521, 파르나스 타워 16층

👋 About us

The Core Research part plays a role in researching and developing the core technologies of the modules that make up NetsPresso to extend and improve their functionalities. Specifically, it conducts research and development on HW-aware AI models through Trainer, explores new lightweight techniques through Compressor, and supports the research and development of new Edge Devices through Converter.


📌 If you join this position

you will research and productize the Quantization technique, one of the core technologies of NetsPresso's Converter module. You will mainly focus on optimizing On-device AI models deployed in NetsPresso or conducting research and development on Nota's unique Quantization techniques.


📙Achievements & Relevant Materials



✅ Key Responsibilities

  • Research and Productization of Quantization Techniques
  • Post-training quantization and quantization-aware training for various deep learning models.
  • Generative AI (such as stable diffusion, large language models, etc.), Computer Vision (including classification, object detection, segmentation, etc.), and other fields.
  • Model Optimization and Conversion for On-device AI
  • Utilizing frameworks like TensorRT, TensorFlow Lite, and others to optimize and convert models for on-device AI applications.



✅ Requirements

  • Applicants with a minimum of 2 years of relevant experience in the mentioned field or equivalent expertise.
  • Applicants should hold a degree in Computer Engineering, Electrical Engineering, or a related discipline.
  • Applicants with a Master's degree or higher, a minimum of 2 years of relevant experience in the field is required.
  • Applicants with experience in research and development of deep learning model optimization using PyTorch framework.
  • Applicants must be eligible for overseas travel without any restrictions.



✅ Pluses

  • Applicants with experience in research and development in the fields of quantization, compression, and kernel optimization.
  • Applicants with experience in optimization tasks related to TensorFlow Lite, TensorRT, ArmNN, or similar libraries, as well as On-Device AI optimization.
  • Applicants with prior experience in porting low-precision deep learning models to embedded devices.
  • Applicants with research and development experience in deep learning model optimization using ML/DL compilers or frameworks such as TVM, Glow, nGraph, XLA, etc.
  • Applicants with a track record of submitting research papers related to deep learning model optimization.



✅ Hiring Process

  • Document Submission → Online Interview → Online Coding Test/Assignment → First-round Interview → Second-round Interview

(Additional tasks may be included between the steps.)



🤓 A Message from the part lead

To be one of the team members, it is crucial to have a high interest in the latest technologies and the ability to bring their ideas into reality. This is not limited to mere research; we are expected to develop unique Quantization techniques that directly relate to the services provided by NetsPresso.
To achieve seamless compatibility and performance improvement within NetsPresso's unique characteristics and with other modules, we value a culture of active communication among the team members. We encourage a proactive attitude in seeking clarity on unfamiliar aspects and the ability to deep-dive into their assigned field, enabling us to grow together every day.



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

Share
[NetsPresso] Quantization Research Engineer

👋 About us

The Core Research part plays a role in researching and developing the core technologies of the modules that make up NetsPresso to extend and improve their functionalities. Specifically, it conducts research and development on HW-aware AI models through Trainer, explores new lightweight techniques through Compressor, and supports the research and development of new Edge Devices through Converter.


📌 If you join this position

you will research and productize the Quantization technique, one of the core technologies of NetsPresso's Converter module. You will mainly focus on optimizing On-device AI models deployed in NetsPresso or conducting research and development on Nota's unique Quantization techniques.


📙Achievements & Relevant Materials



✅ Key Responsibilities

  • Research and Productization of Quantization Techniques
  • Post-training quantization and quantization-aware training for various deep learning models.
  • Generative AI (such as stable diffusion, large language models, etc.), Computer Vision (including classification, object detection, segmentation, etc.), and other fields.
  • Model Optimization and Conversion for On-device AI
  • Utilizing frameworks like TensorRT, TensorFlow Lite, and others to optimize and convert models for on-device AI applications.



✅ Requirements

  • Applicants with a minimum of 2 years of relevant experience in the mentioned field or equivalent expertise.
  • Applicants should hold a degree in Computer Engineering, Electrical Engineering, or a related discipline.
  • Applicants with a Master's degree or higher, a minimum of 2 years of relevant experience in the field is required.
  • Applicants with experience in research and development of deep learning model optimization using PyTorch framework.
  • Applicants must be eligible for overseas travel without any restrictions.



✅ Pluses

  • Applicants with experience in research and development in the fields of quantization, compression, and kernel optimization.
  • Applicants with experience in optimization tasks related to TensorFlow Lite, TensorRT, ArmNN, or similar libraries, as well as On-Device AI optimization.
  • Applicants with prior experience in porting low-precision deep learning models to embedded devices.
  • Applicants with research and development experience in deep learning model optimization using ML/DL compilers or frameworks such as TVM, Glow, nGraph, XLA, etc.
  • Applicants with a track record of submitting research papers related to deep learning model optimization.



✅ Hiring Process

  • Document Submission → Online Interview → Online Coding Test/Assignment → First-round Interview → Second-round Interview

(Additional tasks may be included between the steps.)



🤓 A Message from the part lead

To be one of the team members, it is crucial to have a high interest in the latest technologies and the ability to bring their ideas into reality. This is not limited to mere research; we are expected to develop unique Quantization techniques that directly relate to the services provided by NetsPresso.
To achieve seamless compatibility and performance improvement within NetsPresso's unique characteristics and with other modules, we value a culture of active communication among the team members. We encourage a proactive attitude in seeking clarity on unfamiliar aspects and the ability to deep-dive into their assigned field, enabling us to grow together every day.



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