Lead Machine Learning Engineer

AMD AMD · Semiconductors · Hyderabad, India · Engineering

Lead Machine Learning Engineer at AMD to deliver end-to-end AI/ML solutions by optimizing state-of-the-art neural network architectures for AMD's compute platforms. Responsibilities include compiler development, performance analysis, software framework development, and system-level engineering in a collaborative R&D environment.

What you'd actually do

  1. Work with state-of-the-art AI/ML compiler toolchains across front-end, back-end, optimization, performance, and debugging domains.
  2. Collaborate with the AI/ML Solutions team to accelerate solution development and deployment.
  3. Evaluate and optimize industry-standard and custom neural network architectures, including Vision(CNNs), Vision Transformers (ViTs), and Large Language Models (LLMs), for AMD platforms.
  4. Develop software frameworks, applications, and system-level solutions for machine learning workloads.
  5. Perform performance analysis, simulations, profiling, and optimization of AI applications.

Skills

Required

  • Bachelor's or Master's degree in Computer Science, Computer Engineering, Data Science, Artificial Intelligence, or a related field.
  • Experience with machine learning algorithms and deep learning frameworks.
  • Strong understanding of deep neural network architectures such as CNNs, Vision Transformers (ViTs), and Transformer-based models.
  • Hands-on experience with AI frameworks including: ONNX, PyTorch, TensorFlow, Caffe etc.
  • Experience working with popular machine learning models such as: ResNet, YOLO, Vision Transformer (ViT), BEVFormer, Transformer-based models
  • Excellent C/C++/Python programming and software design skills, including debugging, performance analysis, and test design.

Nice to have

  • Experience collaborating with software partners on, Performance optimization, Benchmark development, Technical collateral creation (presentations, whitepapers, etc.), Joint demonstrations and proof-of-concept solutions
  • Experience working directly with customers to understand and address critical design requirements.
  • Ability to drive adoption of AI/ML compiler technologies through close engagement with customers and cross-functional teams.
  • Experience collaborating with Product Marketing, Applications Engineering, and Architecture teams to define and architect new features.
  • Hands-on experience with: Model Pruning, quantization, Model optimization, Performance tuning, Compiler technologies
  • Knowledge of CUDA/HIP/OpenCL computing
  • Experiences to optimize NPU/GPU/TPU kernels for performance is a plus
  • Exposure to next-generation deep learning compiler technologies.

What the JD emphasized

  • state-of-the-art neural network architectures
  • optimizing them for AMD's next-generation compute platforms
  • compiler development
  • performance analysis
  • compiler optimization
  • software framework development
  • system-level engineering
  • high-performance AI solutions
  • deep learning compiler technologies

Other signals

  • optimizing them for AMD's next-generation compute platforms
  • compiler development
  • performance analysis
  • compiler optimization
  • software framework development
  • system-level engineering