Performance Engineer

Darwin Recruitment

San Francisco (CA)

On-site

USD 170,000 - 250,000

Full time

4 days ago
Be an early applicant

Get a reply from this recruiter

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Darwin Recruitment is seeking a skilled kernel development engineer to own low level kernels for AI model inference workloads. You will craft high performance matrix and attention kernels and collaborate with compiler and architecture teams to optimize speed for the next generation of chips.

Applicants should have strong C++ and low level optimization experience (CUDA or similar), deep knowledge of memory hierarchies, parallelism and profiling, and a proven record of speed ups.

Qualifications

  • Strong C++ and low level optimization experience (CUDA or similar).
  • Knowledge of memory hierarchies, parallelism and profiling.
  • A track record of measurable speed ups.

Responsibilities

  • Develop high performance kernels for matrix and attention workloads
  • Profile and remove bottlenecks across compute and memory
  • Build the kernel library and benchmarking tools
  • Feed results back to the architecture team

Skills

C++
Low-level optimization
CUDA or similar
Profiling & optimization

Job description

About the company: A venture backed AI hardware company building an inference accelerator for the next generation of large model workloads. The company is well funded, has a differentiated architecture, and is moving from design into first silicon, with real customer interest ahead of launch.

Engineering is organized around small teams that own whole problems end to end. Software and hardware engineers work side by side, benchmark against the best GPU results in the industry, and treat every percentage point of efficiency as a competitive edge. The culture is direct, curious and focused on measurable results rather than process.

The role:

You will own the low level kernels that determine how quickly customer models run on the chip. There is no mature kernel library to lean on, so you will build it: matrix multiplies, attention, normalization and the operators that follow, tuned for a new memory and compute architecture.

You will profile real workloads, find where time and bandwidth are lost, and work with the compiler and architecture teams on fixes that change the design as well as the code. The results you produce will show up in customer benchmarks and in the company’s own story about performance.

What you’ll do
  • Develop high performance kernels for matrix and attention workloads
  • Profile and remove bottlenecks across compute and memory
  • Build the kernel library and benchmarking tools
  • Feed results back to the architecture team
What you’ll bring
  • Strong C++ and low level optimization experience (CUDA or similar)
  • Knowledge of memory hierarchies, parallelism and profiling
  • A record of measurable speed ups
Nice to have
  • Non Nvidia target experience (ROCm or custom ISA)
  • GEMM and attention kernel work
  • Assembly or intrinsics
Why join:

Your kernels set the performance customers see, and you will work next to the people designing the chip.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Software Engineer, AI Kernels & Performance Optimization — MTIA Software
Software Engineer, AI Kernels & Performance Optimization — MTIA Software

Meta • Bellevue (WA)

On-site
USD 180,000 - 260,000
Performance Engineer
Performance Engineer

Acceler8 Talent • Mountain View (CA)

On-site
USD 180,000 - 260,000
Member of Technical Staff, GPU Kernels
Member of Technical Staff, GPU Kernels

SF Tensor • San Francisco (CA)

On-site
USD 180,000 - 240,000
Performance Kernel Engineer for AI Inference Accelerators
Performance Kernel Engineer for AI Inference Accelerators

Darwin Recruitment • San Francisco (CA)

On-site
USD 170,000 - 250,000
Kernel Engineer
Kernel Engineer

Acceler8 Talent • San Francisco (CA)

On-site
USD 150,000 - 190,000
KERNEL ENGINEER
KERNEL ENGINEER

Makermaker • San Francisco (CA)

On-site
USD 180,000 - 230,000
Open-source collaboration
Hybrid/On-site flexibility
Competitive compensation
Performance Architect - AI Hardware
Performance Architect - AI Hardware

TEEMA • United States

Remote
USD 140,000 - 210,000
GPU/Kernel Engineer
GPU/Kernel Engineer

Acceler8 Talent • Palo Alto (CA)

On-site
USD 180,000 - 240,000
KERNEL ENGINEER
KERNEL ENGINEER

Makermaker • San Francisco (CA)

On-site
USD 180,000 - 240,000
Performance Engineer
Performance Engineer

Acceler8 • California

On-site
USD 140,000 - 240,000