Senior AI Model Quantization Engineer
Core
Design and implement model optimization features, specifically quantization and compression, for AI workloads on AMD hardware platforms.
Role type
Senior IC software engineer (AI model optimization)
Builds
Production-quality Python tools, libraries, APIs, and framework components for AI inference and training
Domain
AI/ML, Accelerator Hardware, Model Optimization
Deliverable
production ML models
Required skills
C++, Python, PyTorch, ONNX/ONNX Runtime, LLM inference optimization, quantization, low-precision computing, CNN/Transformer/LLM architectures, debugging, performance analysis
Preferred skills
vLLM/SGLang experience, training workflows, runtime integration, accelerator-oriented deployment, AI-assisted development tools
Technologies
PyTorch, ONNX, ONNX Runtime, vLLM, SGLang, C++, Python
Responsibilities
Design and implement model optimization features; Develop quantization and compression capabilities; Build production-quality tools and APIs; Support training and fine-tuning workflows; Analyze and debug accuracy, latency, and memory usage; Collaborate across framework, compiler, runtime, and hardware teams
Seniority
Senior, hands-on IC
