👋 About the Team
The XPU Enabler Team conducts Advanced Research to secure long-term technical competitiveness for NetsPresso. Our primary mission involves analyzing model architectures, establishing optimization strategies, and verifying hardware compatibility to ensure the stable deployment of state-of-the-art AI models in Edge AI environments.
We participate in major government-led AI advancement projects (e.g., K-AI projects and national R&D initiatives), shaping the technical standards and direction of Edge and On-device AI. This position focuses on advanced research that supports both national projects and the long-term roadmap of NetsPresso products, rather than immediate feature development.
📌 What You’ll Do at This Position
As a member of this team, you will preemptively verify the feasibility of running AI models in Edge environments. You will perform model optimization, conversion, and performance analysis to deploy new models onto existing or emerging Edge devices. You will play a pivotal technical role in South Korea’s K-AI projects, with opportunities to engage in the following:
- Planning and documenting technical content for government project proposals.
- Authoring and managing research reports and performance results.
- Engaging in technical discussions and sharing research findings within industry-academic-research consortiums.
- Acting as a "Technical Hub" that bridges the gap between research, experimentation, national projects, and product strategy.
✅ Key Responsibilities
1. Advanced Research & Optimization for Edge AI
- Analyze the architecture of the latest AI models (LLMs, VLMs, Diffusion, Vision models, etc.) and research their feasibility for Edge environments.
- Establish optimization strategies for deploying models on diverse Edge devices (CPU, GPU, NPU, etc.).
- Analyze operational characteristics, memory usage, latency, and throughput.
2. Model Conversion & Execution Verification
- Convert and validate PyTorch-based models into executable formats for Edge environments.
- Conduct experiments using various execution environments such as ONNX, ExecuTorch, and TensorRT.
- Modify model architectures or design alternatives based on HW constraints.
3. Accuracy & Performance Trade-off Analysis
- Analyze accuracy degradation and performance bottlenecks occurring during optimization.
- Propose optimal model configurations and inference strategies tailored for Edge environments.
- Document research results and organize technical insights.
4. Execution of K-AI & Government R&D Projects
- Conduct core technical research for national K-AI and R&D projects.
- Draft technical plans for proposals and manage interim/final reports throughout the project lifecycle.
- Collaborate with external institutions and share research outcomes.
5. Technical Support for NetsPresso Product Development
- Provide technical feedback on product direction based on advanced research findings.
- Propose optimization technologies to be integrated into the NetsPresso platform.
✅ Requirements
- Master’s degree or higher in Computer Science, Electronic Engineering, or a related field. (Bachelor’s degree holders must have at least 2 years of relevant professional experience).
- Deep understanding of deep learning model architectures and inference processes.
- Experience in experimenting with and analyzing PyTorch-based models.
- Ability to quickly learn and experiment with new hardware or frameworks.
- No disqualifying factors for overseas travel.
✅ Pluses
- Experience in research or development related to Edge AI, On-device AI, or model optimization.
- Hands-on experience with Generative AI models (LLM, VLM, Diffusion, etc.).
- Proficiency with inference frameworks such as ONNX, ExecuTorch, or TensorRT.
- Experience deploying models directly on various Edge devices (CPU/GPU/NPU).
- Participation in government R&D or national research projects.
- Published papers or research experience in deep learning optimization and acceleration.
✅ Hiring Process
- Document Screening → 1st Interview → 2nd Interview → 3rd Interview
(Additional assignments may be included during the process.)
🤓 A Message from the Team
Our team covers the entire model lifecycle—from model conversion and graph optimization to vendor compiler integration, device runtime configuration, and deployment—ensuring that LLMs and Computer Vision models run seamlessly on various NPUs, GPUs, and AI accelerators.
Our core mission is to solve challenges that hardware manufacturers do not address, such as Front/Middle-end optimization, Graph Surgery, and operator modification. We strive to make any model run on any device environment.
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
👋 About the Team
The XPU Enabler Team conducts Advanced Research to secure long-term technical competitiveness for NetsPresso. Our primary mission involves analyzing model architectures, establishing optimization strategies, and verifying hardware compatibility to ensure the stable deployment of state-of-the-art AI models in Edge AI environments.
We participate in major government-led AI advancement projects (e.g., K-AI projects and national R&D initiatives), shaping the technical standards and direction of Edge and On-device AI. This position focuses on advanced research that supports both national projects and the long-term roadmap of NetsPresso products, rather than immediate feature development.
📌 What You’ll Do at This Position
As a member of this team, you will preemptively verify the feasibility of running AI models in Edge environments. You will perform model optimization, conversion, and performance analysis to deploy new models onto existing or emerging Edge devices. You will play a pivotal technical role in South Korea’s K-AI projects, with opportunities to engage in the following:
- Planning and documenting technical content for government project proposals.
- Authoring and managing research reports and performance results.
- Engaging in technical discussions and sharing research findings within industry-academic-research consortiums.
- Acting as a "Technical Hub" that bridges the gap between research, experimentation, national projects, and product strategy.
✅ Key Responsibilities
1. Advanced Research & Optimization for Edge AI
- Analyze the architecture of the latest AI models (LLMs, VLMs, Diffusion, Vision models, etc.) and research their feasibility for Edge environments.
- Establish optimization strategies for deploying models on diverse Edge devices (CPU, GPU, NPU, etc.).
- Analyze operational characteristics, memory usage, latency, and throughput.
2. Model Conversion & Execution Verification
- Convert and validate PyTorch-based models into executable formats for Edge environments.
- Conduct experiments using various execution environments such as ONNX, ExecuTorch, and TensorRT.
- Modify model architectures or design alternatives based on HW constraints.
3. Accuracy & Performance Trade-off Analysis
- Analyze accuracy degradation and performance bottlenecks occurring during optimization.
- Propose optimal model configurations and inference strategies tailored for Edge environments.
- Document research results and organize technical insights.
4. Execution of K-AI & Government R&D Projects
- Conduct core technical research for national K-AI and R&D projects.
- Draft technical plans for proposals and manage interim/final reports throughout the project lifecycle.
- Collaborate with external institutions and share research outcomes.
5. Technical Support for NetsPresso Product Development
- Provide technical feedback on product direction based on advanced research findings.
- Propose optimization technologies to be integrated into the NetsPresso platform.
✅ Requirements
- Master’s degree or higher in Computer Science, Electronic Engineering, or a related field. (Bachelor’s degree holders must have at least 2 years of relevant professional experience).
- Deep understanding of deep learning model architectures and inference processes.
- Experience in experimenting with and analyzing PyTorch-based models.
- Ability to quickly learn and experiment with new hardware or frameworks.
- No disqualifying factors for overseas travel.
✅ Pluses
- Experience in research or development related to Edge AI, On-device AI, or model optimization.
- Hands-on experience with Generative AI models (LLM, VLM, Diffusion, etc.).
- Proficiency with inference frameworks such as ONNX, ExecuTorch, or TensorRT.
- Experience deploying models directly on various Edge devices (CPU/GPU/NPU).
- Participation in government R&D or national research projects.
- Published papers or research experience in deep learning optimization and acceleration.
✅ Hiring Process
- Document Screening → 1st Interview → 2nd Interview → 3rd Interview
(Additional assignments may be included during the process.)
🤓 A Message from the Team
Our team covers the entire model lifecycle—from model conversion and graph optimization to vendor compiler integration, device runtime configuration, and deployment—ensuring that LLMs and Computer Vision models run seamlessly on various NPUs, GPUs, and AI accelerators.
Our core mission is to solve challenges that hardware manufacturers do not address, such as Front/Middle-end optimization, Graph Surgery, and operator modification. We strive to make any model run on any device environment.
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.