Sr. Software Development Engineer - AI/ML Frameworks

AMD

San Jose, CA

Full Time

Senior

6 days ago

Job Description

About the Role

AMD is looking for a world class AI frameworks engineer who can provide technical leadership in the development of various AI frameworks in the AMD ecosystem. The role involves driving the technical direction for next generation frameworks for AI model training and inference across a wide variety of AMD devices, including GPUs, accelerators, and datacenter CPUs. The position requires working closely with AI researchers and multiple engineering teams to enhance AI framework capabilities and enable cutting-edge models on AMD hardware. The company's culture emphasizes innovation, collaboration, humility, and inclusiveness, with a mission to build great products that accelerate next-generation computing experiences.

Key Responsibilities

Provide technical leadership in the development of AI frameworks within the AMD ecosystem.
Drive the technical direction for frameworks supporting AI model training and inference on AMD hardware.
Collaborate with AI researchers to develop framework components that efficiently map AI models to hardware accelerators.
Enhance AI framework capabilities, including model optimization features such as graph fusion, quantization, and sparsity.
Work with multiple geographically dispersed engineering teams in a dynamic, fast-paced environment.
Guide other senior developers and domain experts in next-generation framework software development.

Requirements

Experience with development in AI frameworks, AI runtime stacks, or performance tuning and optimizations for workloads on ML accelerator hardware such as GPUs.
Experience with ML frameworks such as PyTorch, OnnxRuntime, JAX, or TensorFlow.
Proficiency in C++ programming.
Experience developing and debugging in Python.
Excellent skills in designing Python tools and libraries used by a large user base.
Experience with AI model architectures, e.g., Transformers, CNNs.
Ability to work effectively in a team environment with geographically distributed members.

Nice to Have

Knowledge of custom accelerator hardware.
Experience with AI software framework benchmarking and profiling.
Operator/kernel development and deployment of models to accelerator (GPU/NPU) stack.
Depth of experience with model optimization, including quantization and sparsity.
Solid understanding of model architectures, LLMs, MoE, diffusion.

Qualifications

BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or related technical fields.

Benefits & Perks

Benefits offered are described: AMD benefits at a glance.

Working at AMD

AMD pushes the limits of innovation to solve the world's most important challenges. The company values being direct, humble, collaborative, and inclusive of diverse perspectives, fostering an environment of execution excellence and technological advancement.

Apply Now