Senior CPU Compiler Performance Engineer

Job Title

Senior CPU Compiler Performance Engineer

Role Summary

Design and implement compiler features and performance optimizations for NVIDIA CPUs, focusing on hardware–software co-design to maximise performance for AI, HPC and data‑centre workloads. The role works within a distributed compiler and systems software organisation collaborating with hardware teams and upstream open source projects.

The engineer will analyze workloads, develop compiler optimizations and code generation improvements, and engage in pre‑silicon performance validation and toolchain development.

Experience Level

Senior — typically 8+ years of relevant experience or equivalent industrial experience.

Responsibilities

Key responsibilities include:

• Design and implement compiler optimizations and code generation targeting NVIDIA CPUs.
• Analyze AI, HPC and performance‑critical workloads to identify optimization opportunities.
• Drive hardware–software co‑design by collaborating with CPU architects and pre‑silicon teams.
• Contribute to upstream and open source compiler projects and integrate improvements into the toolchain.
• Develop and maintain performance validation and benchmarking workflows and tooling.
• Communicate technical results and proposals clearly across geographically distributed teams.

Requirements

Must-have technical skills and experience:

• Extensive experience in compiler development or equivalent hands‑on compiler project work.
• Knowledge of language front‑ends, optimisation techniques, and code generation modules.
• Strong hands‑on C++ programming skills.
• Practical experience with CPU architecture and low‑level performance analysis, including pre‑silicon hardware/software co‑design.
• Excellent verbal and written communication skills for cross‑team collaboration.

Nice-to-have:

• Experience with workload analysis, performance modelling, simulation or advanced performance analysis tools.
• Familiarity with CPU ISAs such as Arm (AArch32/AArch64), RISC‑V, x86_64, PowerPC or DSPs.
• Track record with compiler infrastructures such as GCC, LLVM or MLIR.
• Knowledge of AI algorithms, scientific/HPC applications and related code optimisations.
• Contributions to open source compiler communities.

Education Requirements

BS, MS or higher in Computer Science, Computer Engineering or a related technical field, or equivalent practical work experience (the posting specifies 8+ years of experience as an alternative).

About the Company

Company: NVIDIA

Headquarters: Santa Clara, California, USA

NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.