Compiler Engineer - AI Inference

About NVIDIA

Since inventing the GPU in 1999, NVIDIA has been at the forefront of PC gaming, computer graphics, and parallel computing. More recently, the company's GPU deep learning innovations have propelled modern AI technologies, powering intelligent systems like computers, robots, and autonomous vehicles. Today, NVIDIA is widely recognized as a leader in AI computing.

Role Overview

NVIDIA seeks a highly skilled AI Compiler Engineer to join its premier compiler team, driving groundbreaking advancements in AI performance and technology that will shape the future of computing worldwide.

Key Responsibilities

• Lead and contribute to hands-on development focused on kernel generation and optimization of computational graphs for next-generation NVIDIA GPUs.
• Tackle challenging compilation problems related to AI workloads, encompassing both inference and training, and transition innovative solutions into both enterprise and consumer products.
• Collaborate closely with experts in software, hardware, and research teams to architect and co-design next-generation silicon through hardware/software co-design.
• Support scaling of AI applications in datacenter environments by advancing and optimizing large-scale AI workload deployments.

Required Qualifications

• Possess a BS or MS degree in Computer Science, Computer Engineering, or related disciplines; a PhD is highly preferred.
• Have at least 3 years of professional experience in compiler optimizations, synthesis, and placement within industry settings.
• Demonstrated practical experience working with MLIR (Multi-Level Intermediate Representation).
• Exemplary programming skills in C/C++ and Python, including software design, comprehensive debugging, performance tuning, and test strategy development.
• Strong communication and interpersonal abilities, comfortable collaborating in a fast-moving, product-focused environment.

Preferred Experience

• Experience with hardware implementation of complex AI workloads across CPUs, GPUs, or specialized AI accelerator architectures.
• In-depth knowledge of Large Language Model (LLM) inference and its impact on computer architecture.
• Proven expertise in designing and architecting full compiler frameworks from the ground up.

Additional Information

NVIDIA offers competitive compensation and generous benefits, establishing itself as one of the most sought-after technology employers globally. The company’s rapid growth has expanded its elite engineering teams. If you are an innovative and independent engineer with a passion for advanced technology, NVIDIA encourages you to apply.