Senior AI Model Quantization Engineer
Beijing, ChinaFull-timePosted 1mo ago
About the role
Senior AI Model Quantization Engineer at AMD focusing on model optimization, quantization, and deployment of AI workloads on AMD hardware across CNN, Transformer, LLM, and multimodal models. Role involves developing production-quality tools, collaborating with cross-functional teams, and improving accuracy, latency, and memory usage for real-world AI workloads.
Responsibilities
- Design, implement, and maintain model optimization features for AI workloads on AMD hardware platforms.
- Develop quantization, low-precision, and compression capabilities for CNN, Transformer, LLM, and multimodal models.
- Build production-quality Python tools, libraries, APIs, and framework components.
- Support training and fine-tuning workflows for optimized models.
- Analyze and debug accuracy, latency, memory usage, and deployment tradeoffs.
- Collaborate across framework, compiler, runtime, hardware, and application teams.
Qualifications
- BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, Machine Learning, or related technical fields.
- Experience in AI/ML frameworks, vLLM/SGLang, model optimization, quantization, training workflows, runtime integration, or accelerator-oriented deployment.
- Hands-on experience with ML frameworks such as PyTorch, ONNX/ONNX Runtime, or similar.
- Strong C++/Python development and debugging skills.
- Experience building production-quality tools, libraries, APIs, or framework components.
- Solid understanding of CNN, LLM, or multimodal model architectures.
- Ability to reason about accuracy, performance, latency, memory footprint, and deployment constraints.
- Demonstrated ability to use AI-assisted tools effectively for software development, debugging, technical exploration, and productivity improvement.
- Strong software engineering fundamentals and ability to work with geographically distributed teams.
Skills
Required:Model optimizationQuantization and low-precisionPythonC++PyTorch/ONNX
Last updated Oct 15, 2026. Interested? Apply on the company site.
About AMD
together we advance_AI
AMD delivers leadership high-performance and adaptive computing solutions to advance data center AI, AI PCs, intelligent edge devices, gaming, & beyond.
AIData CenterHigh-Performance ComputingGamingEdge Devices
More open roles at AMD
- System Thermal Design Staff Engineer4d agoPenang, Malaysia · Engineering
- PD Engineer4d agoHybrid (Bangalore) · Engineering
- PD Engineer4d agoBangalore · Engineering
- Low-Power & CDC Verification Engineer4d agoSanta Clara, California · Engineering
- Technical Program Manager4d agoShanghai · Engineering