Remote Senior Kernel Engineer for AI Hardware & ML Compute

MatX; Mountain View (CA); Hybrid; USD 160,000 - 600,000; Full time

Benefits offered by this job

4 weeks PTO (accrued)

Medical, dental and vision insurance

Life insurance

HSA/FSA via Lively

Professional development budget

Team meals onsite

Commute reimbursement

MatX Extras: $50/mo

Cell & Internet stipend

Mental health benefits

Parental leave support

AI resources stipend

Job summary

MatX is building a compute platform for AGI and is seeking a hands-on TLM to lead the Kernel team in Mountain View. You will mentor engineers, design high-performance compute kernels, and align hardware and software with the ML and hardware teams to push the boundaries of AI workloads.

You will contribute by implementing kernels, guiding architecture decisions, and translating complex trade-offs for founders and stakeholders while ensuring a strong software-hardware integration.

Qualifications

• 2+ years of engineering team management experience.
• 7+ years of experience in engineering teams.
• Bachelor of Computer Science or equivalent degree.
• Experience optimizing software for specialized hardware and techniques like parallelism, SIMD, C, assembly, or GPU/CUDA.

Responsibilities

• Manage, mentor, and build a team of kernel engineers and software developers.
• Design and optimize kernels that interface with our hardware.
• Work with ML Research and Hardware Engineering teams.
• Provide guidance on hardware architecture from a programmer's perspective, ensuring integration with the software stack.

Skills

Kernel engineering

Team management

C/C++

CUDA

Rust

Zig

Assembly

GPU programming

Education

Bachelor of Computer Science

Tools

CUDA Toolkit

GPU Tools

Job description

MatX is building a compute platform for AGI and is seeking a hands-on TLM to lead the Kernel team in Mountain View. You will mentor engineers, design high-performance compute kernels, and align hardware and software with the ML and hardware teams to push the boundaries of AI workloads.

You will contribute by implementing kernels, guiding architecture decisions, and translating complex trade-offs for founders and stakeholders while ensuring a strong software-hardware integration.