AI Frameworks Software Engineer (AI)

TL;DR

AI Frameworks Software Engineer (AI): Developing and optimizing model compression algorithms and tools for hirify.global AI platforms with an accent on quantization and pruning techniques for LLMs and generative models. Focus on implementing high-performance inference solutions, tracking cutting-edge deployment research, and ensuring model efficiency across CPUs, GPUs, and specialized AI accelerators.

Location: Must be based in Shanghai, China

Company

hirify.global is a leading global technology company specializing in semiconductor manufacturing, AI platform development, and innovative computing hardware.

What you will do

• Develop and maintain hirify.global Neural Compressor products and related tools like auto-round.
• Optimize software performance for hirify.global AI platforms, including CPUs, GPUs, and AI accelerators.
• Research and implement advanced quantization and compression techniques for Large Language Models (LLMs) and generative media models.
• Track and explore industry trends in efficient model deployment and inference/finetuning acceleration.

Requirements

• Master’s or PhD degree in Computer Science or a related field.
• Solid understanding of deep learning frameworks and Large Language Model (LLM) fundamentals.
• Proficiency in Python and C++ development.
• Familiarity with model compression techniques such as quantization and pruning.
• Ability to work on-site in Shanghai, China.
• Strong oral and written English skills.

Nice to have

• Experience in model fine-tuning or inference optimization tool development.
• Proven problem-solving skills and self-motivation in technical environments.

Culture & Benefits

• Opportunities for continuous learning and career advancement within a global corporation.
• Access to world-class hardware and AI research environments.
• Commitment to ethical hiring practices and RBA compliance.
• Collaborative team environment focused on technological innovation.