At AMD, our mission is to build great products that accelerate next-generation computing experiences—from AI and data centers, to PCs, gaming and embedded systems, and we are looking for a Director, Machine Learning to join our AI/ML Model Compiler and Applications team to address the challenge of training generative AI.
Requirements
- Experience with ML frameworks such as Onnx, PyTorch, or TensorFlow.
- Experience with distributed training and distributed training frameworks, such as DeepSpeed.
- Experience with LLMs or computer vision, especially large models, is a plus.
- Excellent C++ and Python programming skills, including debugging, profiling, and performance analysis.
- Experience with ML pipelines.
- Understanding of NPU hardware architecture
- Defining scalable algorithms that enables efficient problem mapping
Responsibilities
- Lead a growing team focused on research, design, and implement novel methods for efficient Generative AI.
- Experience in developing ML compilers for low power inference architecture
- Experience in all 3 stages of ML compiler- front end, middle end and backend
- Experience in defining optimized tiling algorithms, fusion algorithms at different memory hierarchy
- Influence the direction of AMD AI platform.
- Propose and apply innovative model quantization, sparsity, and acceleration algorithms on various AMD platform, e.g., GPU/CPU/AIE.
- Collaborate with software and hardware team to E2E co-optimize model performance.
Other
- A PhD or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field.
- Strong communication and problem-solving skills.
- Strong leadership and management skills.
- LOCATION: San Jose, CA preferred, Austin, TX may be considered
- AMD benefits at a glance.
