Remote Mojo Libraries Engineer GPU Kernel & Performance

Modular; United States; Hybrid; USD 167,000 - 286,000; Full time

Benefits offered by this job

Stock options

Premium insurance plans

5% 401k matching

Flexible paid time off

Job summary

Modular is building Mojo, a high-performance language stack for AI. As a Mojo Libraries Engineer, you will design core abstractions across the Mojo Standard Library and kernel libraries to empower developers and accelerate AI workloads.

You will optimize performance on GPUs and CPUs, collaborate across compiler, kernel, and runtime teams, and engage with the open source community. This role supports in-office Los Altos, CA or remote work from home in the US/Canada.

Qualifications

• Experience with GPU programming languages like CUDA or OpenCL.
• Deep understanding of GPU architecture (memory hierarchies, tensor cores) and how it influences design.
• Proficiency in C++, Rust, or Swift with low-level programming and optimization skills.
• Hands-on open source experience or maintenance/review of community submissions.
• Collaborative mindset and problem-solving in a high-performing team.

Responsibilities

• Design APIs across the Mojo Standard Library and kernel libraries to shape developer experience.
• Create abstractions enabling kernel and algorithm development on GPUs and CPUs for GenAI stack.
• Optimize library functionality for performance, memory efficiency, and hardware utilization.
• Participate in design discussions and code reviews to uphold engineering standards.
• Collaborate with other teams to align the standard library with platform needs.
• Contribute to an open source project and engage with the community.

Skills

CUDA/OpenCL programming

GPU architecture knowledge

C++/Rust/Swift systems languages

Open source contribution

Collaborative teamwork

Tools

LLVM/MLIR/Python exposure

Job description

Modular is building Mojo, a high-performance language stack for AI. As a Mojo Libraries Engineer, you will design core abstractions across the Mojo Standard Library and kernel libraries to empower developers and accelerate AI workloads.

You will optimize performance on GPUs and CPUs, collaborate across compiler, kernel, and runtime teams, and engage with the open source community. This role supports in-office Los Altos, CA or remote work from home in the US/Canada.