Description

You will build and maintain profiling and trace tools to analyze and enhance multi-node system performance for AI accelerators and high-performance compute platforms.

This role is on-site.

Responsibilities

• Integrate software components with user-mode drivers for AI accelerators.
• Perform low-level debugging and performance tuning of GPU-enabled systems.
• Investigate and resolve complex software and hardware interaction issues across the technology stack.
• Optimize performance, scalability, and reliability of embedded and compute systems.
• Collaborate with hardware, firmware, and software teams to deliver system-level solutions.

Required Skills

• 5+ years of hands-on C++ development for system-level or embedded applications.
• Strong understanding of GPU architectures and performance optimization techniques.
• Experience with embedded software and hardware interaction layers.
• Proficiency in low-level debugging and performance analysis tools.
• Knowledge of C programming for systems and driver-level development.
• Experience diagnosing complex cross-layer issues involving hardware, firmware, and software.
• B.Sc. or higher in Computer Science, Electrical Engineering, or a related field.

Preferred Skills

• Understanding of user-mode driver development and system profiling tools.

Key Skills

Education

Any Graduate