👋 About the Team
The NetsPresso Core Research Team develops the core technologies that power NetsPresso. We convert deep learning models from various framework IRs (Intermediate Representations) into a unified IR, and develop optimization techniques—such as graph optimization, quantization, and compression—to make them lightweight and accelerated for specific hardware environments. Our research focuses on enabling a wide range of AI models—from Computer Vision to Generative AI—to run efficiently across diverse platforms, from edge devices to data center servers.
We continuously enhance NetsPresso’s performance and scalability through new lightweighting methods and cross-hardware compatibility improvements. In particular, we focus on optimizing AI models from a graph perspective, simplifying structures, improving execution speed, and performing model transformations tailored to hardware constraints—all while maintaining accuracy.
📌 What You’ll Do at This Position
As an AI Optimization Engineer, you’ll work on optimizing AI models from a graph perspective — improving execution speed while maintaining accuracy, all while taking into account the unique characteristics of each target hardware. You’ll stay up to date with the latest research trends and apply them directly to your work, ultimately contributing to the realization of NetsPresso’s core product.
In this role, you’ll experience the entire journey of AI model optimization — from cutting-edge theory and implementation to real-world productization.
✅ Key Responsibilities
- Improve AI model performance through graph optimization
- Simplify model structures via operation removal, fusion, substitution, and composition
- Enhance speed and memory efficiency while preserving model accuracy
- Optimize across various AI frameworks (ONNX, PyTorch, ExecuTorch, etc.)
- Optimize AI models for diverse architectures and hardware
- Work with a wide range of models including Generative AI (LLMs, VLMs, Diffusion models) and Computer Vision
- Adapt and accelerate models for GPU, NPU, and CPU environments
✅ Requirements
- Bachelor’s, Master’s, or Ph.D. degree in Computer Science, Electrical/Electronic Engineering, or a related field
- For bachelor’s degree holders: at least 2 years of relevant experience or equivalent capability
- No restrictions on overseas travel
- Hands-on experience with PyTorch, ONNX, Python, Linux, Git/GitHub, and Docker
✅ Pluses
- Experience with CUDA or custom NPU SDKs
- Familiarity with AI frameworks and tools such as ExecuTorch, TFLite, TensorRT, or Hugging Face
- Experience serving LLMs using vLLM, Llama.cpp, Ollama, or SGLang
- Experience publishing academic papers or presenting at conferences
- Proficiency in English sufficient for overseas collaboration and conference presentations
✅ Hiring Process
- Document Screening → Assignment → 1st Interview → 2nd Interview
(Additional assignments may be included during the process.)
🤓 A Message from the Team
The Core Research Team values both technical depth and collaborative problem-solving. We tackle complex optimization challenges, explore new directions in model efficiency, and actively exchange ideas to identify the most effective solutions.
If you enjoy deeply understanding technology, designing efficient structures, and sharing that journey with your team, you’ll find the Core Research Team a place where you can grow and make meaningful impact together.
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
The NetsPresso Core Research Team develops the core technologies that power NetsPresso. We convert deep learning models from various framework IRs (Intermediate Representations) into a unified IR, and develop optimization techniques—such as graph optimization, quantization, and compression—to make them lightweight and accelerated for specific hardware environments. Our research focuses on enabling a wide range of AI models—from Computer Vision to Generative AI—to run efficiently across diverse platforms, from edge devices to data center servers.
We continuously enhance NetsPresso’s performance and scalability through new lightweighting methods and cross-hardware compatibility improvements. In particular, we focus on optimizing AI models from a graph perspective, simplifying structures, improving execution speed, and performing model transformations tailored to hardware constraints—all while maintaining accuracy.
📌 What You’ll Do at This Position
As an AI Optimization Engineer, you’ll work on optimizing AI models from a graph perspective — improving execution speed while maintaining accuracy, all while taking into account the unique characteristics of each target hardware. You’ll stay up to date with the latest research trends and apply them directly to your work, ultimately contributing to the realization of NetsPresso’s core product.
In this role, you’ll experience the entire journey of AI model optimization — from cutting-edge theory and implementation to real-world productization.
✅ Key Responsibilities
- Improve AI model performance through graph optimization
- Simplify model structures via operation removal, fusion, substitution, and composition
- Enhance speed and memory efficiency while preserving model accuracy
- Optimize across various AI frameworks (ONNX, PyTorch, ExecuTorch, etc.)
- Optimize AI models for diverse architectures and hardware
- Work with a wide range of models including Generative AI (LLMs, VLMs, Diffusion models) and Computer Vision
- Adapt and accelerate models for GPU, NPU, and CPU environments
✅ Requirements
- Bachelor’s, Master’s, or Ph.D. degree in Computer Science, Electrical/Electronic Engineering, or a related field
- For bachelor’s degree holders: at least 2 years of relevant experience or equivalent capability
- No restrictions on overseas travel
- Hands-on experience with PyTorch, ONNX, Python, Linux, Git/GitHub, and Docker
✅ Pluses
- Experience with CUDA or custom NPU SDKs
- Familiarity with AI frameworks and tools such as ExecuTorch, TFLite, TensorRT, or Hugging Face
- Experience serving LLMs using vLLM, Llama.cpp, Ollama, or SGLang
- Experience publishing academic papers or presenting at conferences
- Proficiency in English sufficient for overseas collaboration and conference presentations
✅ Hiring Process
- Document Screening → Assignment → 1st Interview → 2nd Interview
(Additional assignments may be included during the process.)
🤓 A Message from the Team
The Core Research Team values both technical depth and collaborative problem-solving. We tackle complex optimization challenges, explore new directions in model efficiency, and actively exchange ideas to identify the most effective solutions.
If you enjoy deeply understanding technology, designing efficient structures, and sharing that journey with your team, you’ll find the Core Research Team a place where you can grow and make meaningful impact together.
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