Compiler Engineer - AI Inference

About NVIDIA and the Role

Since revolutionizing the PC gaming market and computer graphics with the invention of the GPU in 1999, NVIDIA has evolved to become a leader in parallel computing and AI. Today, recognized as the AI computing company, NVIDIA's GPUs power intelligent machines such as robots and self-driving vehicles that perceive and understand their environment.

We are currently looking for an exceptional AI Compiler Engineer to join our leading-edge compiler team. This role will involve advancing AI performance by developing technologies that drive the next wave of computing innovation on a global scale.

Key Responsibilities

• Lead the innovation of AI compiler technology by directly developing kernel generation and computational graph optimizations tailored for upcoming NVIDIA GPUs.
• Address complex compilation challenges specific to AI for both inference and training workloads, translating these advancements into enterprise and consumer-level products.
• Engage in collaborative hardware and software co-design with experts across software, hardware, and research divisions to shape future silicon architectures.
• Contribute to scaling AI workloads effectively in datacenter environments through optimization and advancement efforts.

Qualifications and Experience

• Bachelor's or Master's degree in Computer Science, Computer Engineering, or a related field is required; a PhD is highly preferred.
• Minimum of three years of industry experience focused on compiler optimization, synthesis, and placement techniques.
• Proven practical experience working with MLIR (Multi-Level Intermediate Representation).
• Exceptional programming skills in C/C++ and Python, combined with strong software design capabilities, debugging expertise, performance profiling, and test engineering acumen.
• Excellent communication and interpersonal skills enabling effective teamwork within fast-paced, product-focused environments.

Additional Desired Skills

• Experience implementing sophisticated AI workloads across CPUs, GPUs, or custom AI accelerator hardware.
• Deep knowledge of Large Language Model (LLM) inference and its impact on computer architecture.
• Strong skills in designing and architecting end-to-end compiler frameworks from the ground up.

Additional Information

NVIDIA offers competitive compensation and an extensive benefits package, making it a leading employer in the technology sector. Our engineering teams are expanding rapidly due to growth, welcoming creative and independent engineers passionate about innovation and technology.

Reference Code: JR2023372