👋 About the Team
The XPU Enabler team ensures AI models run smoothly across a wide range of devices. Whenever a new AI model or hardware device emerges, we address compatibility issues and build automated performance profiling services to create seamless connections between models and devices. Our team brings together specialists from various domains—ML Engineers, Embedded Engineers, Backend/Frontend/Mobile Engineers, and AI Software Engineers—working closely together to solve complex technical challenges by leveraging their individual areas of expertise.
📌 What You’ll Do at This Position
You’ll collaborate with top-tier NPU vendors and clients looking to optimize AI models for deployment on various NPUs. Your focus will be on LLMs and similar models, building a strong foundation in core technologies such as static graph transformation, optimization, quantization, and device-level profiling. Through this, you’ll gain a deep understanding of NPU-specific optimization methods and acquire hands-on experience in model deployment—developing your capabilities as a highly skilled AI engineer.
✅ Key Responsibilities
- Develop inference pipelines for deploying NPU-optimized LLM models on edge devices.
- Profile model performance on edge devices, focusing on accuracy, memory consumption, and latency.
✅ Requirements
- 2+ years of relevant experience in the following fields:
- Experience accelerating AI models on NPUs.
- Hands-on experience developing applications in C++ that deploy AI model inference on edge devices.
- Understanding of LLM input/output, caching, and decoding algorithms.
- No restrictions on international travel
✅ Pluses
- Experience with quantization of LLMs and hands-on implementation.
- Extensive experience modifying AI models to extract static graph representations (e.g., jit, onnx).
- Experience using Executorch for model quantization, compilation, and inference.
✅ Hiring Process
- Document Screening → Screening Interview → Assignment → 1st Interview → 2nd Interview
🤓 A Message from the Team
The XPU Enabler Team takes full ownership of the entire pipeline—from AI model development to real-world device deployment. We don’t limit ourselves to specific frameworks or devices. Instead, we thrive on flexibility and a strong problem-solving mindset as we work across diverse models and NPU environments.
Our team values technical depth, cross-functional respect, and shared growth. If you enjoy exploring new technologies and tackling unfamiliar challenges with curiosity and creativity, you'll feel right at home with us.
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 XPU Enabler team ensures AI models run smoothly across a wide range of devices. Whenever a new AI model or hardware device emerges, we address compatibility issues and build automated performance profiling services to create seamless connections between models and devices. Our team brings together specialists from various domains—ML Engineers, Embedded Engineers, Backend/Frontend/Mobile Engineers, and AI Software Engineers—working closely together to solve complex technical challenges by leveraging their individual areas of expertise.
📌 What You’ll Do at This Position
You’ll collaborate with top-tier NPU vendors and clients looking to optimize AI models for deployment on various NPUs. Your focus will be on LLMs and similar models, building a strong foundation in core technologies such as static graph transformation, optimization, quantization, and device-level profiling. Through this, you’ll gain a deep understanding of NPU-specific optimization methods and acquire hands-on experience in model deployment—developing your capabilities as a highly skilled AI engineer.
✅ Key Responsibilities
- Develop inference pipelines for deploying NPU-optimized LLM models on edge devices.
- Profile model performance on edge devices, focusing on accuracy, memory consumption, and latency.
✅ Requirements
- 2+ years of relevant experience in the following fields:
- Experience accelerating AI models on NPUs.
- Hands-on experience developing applications in C++ that deploy AI model inference on edge devices.
- Understanding of LLM input/output, caching, and decoding algorithms.
- No restrictions on international travel
✅ Pluses
- Experience with quantization of LLMs and hands-on implementation.
- Extensive experience modifying AI models to extract static graph representations (e.g., jit, onnx).
- Experience using Executorch for model quantization, compilation, and inference.
✅ Hiring Process
- Document Screening → Screening Interview → Assignment → 1st Interview → 2nd Interview
🤓 A Message from the Team
The XPU Enabler Team takes full ownership of the entire pipeline—from AI model development to real-world device deployment. We don’t limit ourselves to specific frameworks or devices. Instead, we thrive on flexibility and a strong problem-solving mindset as we work across diverse models and NPU environments.
Our team values technical depth, cross-functional respect, and shared growth. If you enjoy exploring new technologies and tackling unfamiliar challenges with curiosity and creativity, you'll feel right at home with us.
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