Compiler Engineer - AI Inference

About NVIDIA

NVIDIA, known for inventing the GPU in 1999 that transformed PC gaming, computer graphics, and parallel computing, has become the leader in AI computing. Their GPUs serve as the core processors behind computers, robots, and autonomous vehicles capable of perceiving and understanding their environments.

Role Overview

We are looking for an outstanding AI Compiler Engineer to join our elite compiler team, pushing the boundaries of AI performance and developing technology that supports the upcoming era of computing. This role offers a chance to impact the global technology landscape significantly.

Key Responsibilities

• Lead technological advancements via hands-on development focused on kernel generation and optimizing computational graphs for next-generation NVIDIA GPUs.
• Address and resolve complex compilation challenges related to AI workloads, including both inference and training, and successfully implement these solutions into commercial products.
• Work closely with experts in software, hardware, and research departments to collaboratively design and architect future silicon hardware.
• Contribute to scaling AI solutions to datacenter environments by enhancing the deployment and performance of large-scale AI workloads.

Required Qualifications

• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related discipline; PhD candidates are highly preferred.
• At least 3 years of professional experience in compiler optimization, synthesis, and placement within industry settings.
• Proven practical experience working with MLIR frameworks.
• Exceptional programming expertise in C/C++ and Python, including advanced debugging, performance analysis, and test design skills.
• Excellent communication and interpersonal abilities, enabling effective teamwork in a dynamic and product-focused environment.

Preferred Qualifications

• Practical experience implementing complex AI workloads on CPU, GPU, or custom AI accelerator architectures.
• Strong understanding of Large Language Model (LLM) inference and its impact on computer system architecture.
• Experience in designing and architecting comprehensive compiler frameworks from inception.

Additional Information

We offer competitive compensation packages and comprehensive benefits. Our teams consist of some of the most innovative and dedicated professionals in technology, and due to rapid expansion, our exclusive engineering groups are growing. If you are passionate about technology, creative, and self-driven, we invite you to join us.