AI Frameworks Software Engineer (Model Compression)

Location: On-site in Shanghai, China

Company

hirify.global develops AI framework technologies and model-compression tools for deployment on CPUs, GPUs, and AI accelerators.

What you will do

• Develop Intel Neural Compressor and its core algorithm tools, including AutoRound.
• Optimize model-compression technologies for Intel CPUs, GPUs, and AI accelerators.
• Research and implement quantization and compression techniques for large language, vision-language, and generative models.
• Work with text-to-image, text-to-video, and world-model applications.
• Explore efficient model deployment, inference acceleration, and fine-tuning acceleration.
• Contribute to algorithm research, product feature development, performance optimization, and open-source projects.

Requirements

• Bachelor’s or master’s degree in Computer Science or a related field.
• Solid understanding of deep learning, deep learning frameworks, and large language model fundamentals.
• Familiarity with model-compression techniques, including quantization and pruning.
• Proficiency in Python, C++, or other programming languages commonly used in deep learning development.
• Good verbal and written English communication skills required.
• Strong teamwork and collaboration skills.

Nice to have

• Experience with model fine-tuning, inference optimization, or related tool development.
• Strong self-motivation, ownership, and problem-solving skills.
• Passion for technological innovation and practical engineering.

Culture & Benefits

• Full-time college graduate position.
• Shift 1 schedule in China.
• Commitment to continuous exploration and improvement.
• Equal employment consideration in accordance with local law.
• No recruitment, medical examination, or other hiring fees are charged to candidates.