1. Responsible for optimizing and deploying AI models on mobile devices to improve the performance and response speed of AI applications.
2. Collaborate with team members, participate in the analysis of requirements, architecture design, and code implementation of the mobile inference engine.
3. Stay updated on the latest technological advancements in both the academic and industrial sector
Requirements
• Bachelor's degree or above in a computer-related field with a solid foundation in computer theory.
• Solid foundation in data structures and algorithms, proficient in C++ programming with good coding habits and style.
• Familiar with ARM architecture, experience in ARM Neon Intrinsics/Assembly development.
• Familiar with AI model deployment, experience with open-source inference engines is a plus, such as MNN, TNN, TFLITE, etc.
• Understanding of AI acceleration technologies, familiarity with model compression, model quantization, model pruning, TVM, and similar technologies is a plus.
• Familiarity with deep learning frameworks such as TensorFlow, PyTorch, with practical usage and optimization experience, is advantageous.
Business Registration Number : 200611680D | Licence Number : 10C5117 | EA Registration Number : R1659662
