AI Frameworks Software Engineer – Model Compression
Shanghai
Workplace: OnsiteFull timeFunction: Software EngineeringEducation: bachelorsSkills: ["Teamwork","Collaboration","Problem-solving","Communication","Self-motivation"]Join the Intel Neural Compressor team to develop model compression technologies, including AutoRound and core algorithm tools, and optimize them for Intel AI platforms across CPUs, GPUs, and AI accelerators. You will research and implement quantization and compression for LLMs and multimodal generative models, explore efficient deployment and inference acceleration, and contribute to fine-tuning acceleration and open-source initiatives.
Loading
Loading job details...
Preparing the role view and application actions.

