Senior ML Compiler Engineer for AI Accelerators

Advanced Micro Devices; San Jose (CA); Hybrid; USD 140,000 - 210,000; Full time

Job summary

AMD has a broad portfolio of several ML accelerator devices with NPUs (neural processing units) that are integrated in its Client and Embedded product portfolio. The Vitis unified platform (Vitis Unified Software Platform) targets several AMD Embedded accelerator cards.

The Ryzen AI software platform (Ryzen AI Software) targets several client CPU devices. Both these devices have NPUs that are based of AMD's proprietary AI-engine architecture.

Qualifications

• Strong programming skills in C++.
• Experience with compilation stack to any custom hardware accelerator.
• Knowledge of MLIR and dialects is an added plus.
• Prior work using modern source control such as GitHub.
• Knowledge of machine learning model structures.
• Experience with AI agents for development or qualification tasks.

Responsibilities

• Work on a new compiler alongside senior developers and domain experts.
• Collaborate across engineering teams in a dynamic, fast-paced environment.
• Contribute to roadmap efforts to build next-generation compiler from the bottom up.
• Apply data-driven analysis and optimization techniques.
• Debug, analyze, and resolve issues while exploring efficient alternatives.

Skills

C++

Compiler tools

MLIR knowledge

GitHub

Machine learning concepts

AI agent experience

Education

Bachelor's or Master's in Computer Science/Engineering

Tools

MLIR

GitHub

C++ toolchains

Job description

AMD has a broad portfolio of several ML accelerator devices with NPUs (neural processing units) that are integrated in its Client and Embedded product portfolio. The Vitis unified platform (Vitis Unified Software Platform) targets several AMD Embedded accelerator cards.

The Ryzen AI software platform (Ryzen AI Software) targets several client CPU devices. Both these devices have NPUs that are based of AMD's proprietary AI-engine architecture.