👋 About the Team
NetsPresso converts various framework IRs into a unified IR and optimizes models for each hardware environment to run faster and more efficiently. The Core Research team develops the core modules that enable this, working on key optimization techniques such as graph optimization, quantization, and compression. We focus on improving performance and compatibility so models run reliably across a wide range of devices, from edge hardware to data center servers.
📌 What You’ll Do at This Position
You will research NetsPresso’s core technologies, including the latest quantization and graph optimization methods, and explore ways to increase model speed while maintaining accuracy across different hardware environments. You will also take part in designing Nota’s optimization strategies and implementing them in the actual product, gaining broad experience with on-device AI models and optimization techniques.
👉 Check what core research team has done here.
✅ Key Responsibilities
On-device AI Model Optimization and Conversion
- Optimize and convert models utilizing various frameworks such as ExecuTorch, ONNX, and TensorRT
- Improve AI model performance through graph optimization and support compression techniques like Pruning and Quantization.
Support Optimization for Various AI Models
- Generative AI (Large Language Models, Stable Diffusion, etc.)
- Computer Vision (Classification, Object Detection, Segmentation, etc.) and AI models in other domains.
- Analyze AI model performance and support improvement efforts.
✅ Requirements
- Current students or degree holders in Computer Engineering, Electrical Engineering, or related fields
- Proficiency in Python development and relevant project experience
- Experience in optimizing PyTorch-based deep learning models
- No disqualifications for overseas travel
✅ Pluses
- R&D experience in Quantization, Graph Optimization, and Model Compression
- Experience with AI frameworks, tools, and platforms such as ExecuTorch, TFLite, TensorRT, and Hugging Face
- Experience porting low-bit models to embedded devices
- Experience with LLM serving solutions such as vLLM, Llama.cpp, Ollama, and SGLang
- Experience publishing research papers related to deep learning model optimization
✅ Hiring Process
- Document Screening → 1st Interview (On-site Coding Test / Resume Review)
(Additional assignments may be included during the process.)
✅ Internship Duration
- 6 months (Open to discussion)
🤓 A Message from the Team
A strong curiosity for new technologies and the ability to turn ideas into real impact are essential in this role. You won’t be doing research for its own sake—you’ll be developing original model-optimization technologies that directly power the NetsPresso service. Because each module is tightly interconnected, we place great value on active communication and a proactive mindset. If you enjoy diving deep into complex technical challenges and growing through close collaboration, you’ll thrive and achieve meaningful results with this 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.
- Veterans and individuals with disabilities will receive preferential treatment in accordance with relevant regulations.
🔎 Helpful materials
👋 About the Team
NetsPresso converts various framework IRs into a unified IR and optimizes models for each hardware environment to run faster and more efficiently. The Core Research team develops the core modules that enable this, working on key optimization techniques such as graph optimization, quantization, and compression. We focus on improving performance and compatibility so models run reliably across a wide range of devices, from edge hardware to data center servers.
📌 What You’ll Do at This Position
You will research NetsPresso’s core technologies, including the latest quantization and graph optimization methods, and explore ways to increase model speed while maintaining accuracy across different hardware environments. You will also take part in designing Nota’s optimization strategies and implementing them in the actual product, gaining broad experience with on-device AI models and optimization techniques.
👉 Check what core research team has done here.
✅ Key Responsibilities
On-device AI Model Optimization and Conversion
- Optimize and convert models utilizing various frameworks such as ExecuTorch, ONNX, and TensorRT
- Improve AI model performance through graph optimization and support compression techniques like Pruning and Quantization.
Support Optimization for Various AI Models
- Generative AI (Large Language Models, Stable Diffusion, etc.)
- Computer Vision (Classification, Object Detection, Segmentation, etc.) and AI models in other domains.
- Analyze AI model performance and support improvement efforts.
✅ Requirements
- Current students or degree holders in Computer Engineering, Electrical Engineering, or related fields
- Proficiency in Python development and relevant project experience
- Experience in optimizing PyTorch-based deep learning models
- No disqualifications for overseas travel
✅ Pluses
- R&D experience in Quantization, Graph Optimization, and Model Compression
- Experience with AI frameworks, tools, and platforms such as ExecuTorch, TFLite, TensorRT, and Hugging Face
- Experience porting low-bit models to embedded devices
- Experience with LLM serving solutions such as vLLM, Llama.cpp, Ollama, and SGLang
- Experience publishing research papers related to deep learning model optimization
✅ Hiring Process
- Document Screening → 1st Interview (On-site Coding Test / Resume Review)
(Additional assignments may be included during the process.)
✅ Internship Duration
- 6 months (Open to discussion)
🤓 A Message from the Team
A strong curiosity for new technologies and the ability to turn ideas into real impact are essential in this role. You won’t be doing research for its own sake—you’ll be developing original model-optimization technologies that directly power the NetsPresso service. Because each module is tightly interconnected, we place great value on active communication and a proactive mindset. If you enjoy diving deep into complex technical challenges and growing through close collaboration, you’ll thrive and achieve meaningful results with this 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.
- Veterans and individuals with disabilities will receive preferential treatment in accordance with relevant regulations.
🔎 Helpful materials