GPU Kernel & Performance Engineer for Fast LLMs on NVIDIA

Commonai C.I.C.

Cambourne

On-site

GBP 90,000 - 130,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Competitive salary
Pension
Professional development
Networking opportunities
Office near Cambridge

Job summary

CommonAI CIC in the Cambridge area is seeking a GPU Kernel and Performance Engineer to accelerate research models on NVIDIA GPUs. You will turn model designs into fast CUDA/Triton code and measure time/memory on real hardware.

You'll work with a small research team, optimize for memory hierarchy and participate in porting components to different accelerators. A strong grounding in GPU architecture and rigorous testing is essential.

Qualifications

  • Proven experience writing and optimising GPU kernels in CUDA or Triton.
  • Strong understanding of GPU architecture and memory hierarchies (shared memory, HBM bandwidth, memory coalescing).
  • Hands-on experience profiling and optimising performance with Nsight Compute / Nsight Systems.
  • Strong Python and C/C++.
  • Rigorous testing of numerical code (mixed-precision, reference comparisons).
  • Willingness to learn new hardware architectures and programming models.

Responsibilities

  • Write and optimise CUDA and Triton kernels for NVIDIA GPUs.
  • Adapt and extend open-source kernels to new models and designs.
  • Profile training and inference to identify time and memory bottlenecks.
  • Optimise for memory hierarchy and device-specific features.
  • Build tooling to measure data movement per token and validate models against hardware measurements.
  • Collaborate with training engineers to boost throughput and with researchers to test new designs.

Skills

CUDA kernel programming
Triton kernel programming
GPU architecture & memory hierarchy
NVIDIA Nsight Compute / Nsight Systems
Python
C/C++
Performance profiling

Education

Advanced degree in CS/EE or equivalent experience

Tools

FlashAttention-style kernels
CUTLASS
CuTe
NCCL
NVLink

Job description

CommonAI CIC in the Cambridge area is seeking a GPU Kernel and Performance Engineer to accelerate research models on NVIDIA GPUs. You will turn model designs into fast CUDA/Triton code and measure time/memory on real hardware.

You'll work with a small research team, optimize for memory hierarchy and participate in porting components to different accelerators. A strong grounding in GPU architecture and rigorous testing is essential.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

GPU Kernel & Performance Engineer — CUDA/Triton Expert
GPU Kernel & Performance Engineer — CUDA/Triton Expert

CommonAI C.I.C. • Cambridge

On-site
GBP 120,000 - 170,000
Competitive salary
Pension
Professional development
+1
CUDA/Triton Kernel Engineer for Fast AI Inference
CUDA/Triton Kernel Engineer for Fast AI Inference

CommonAI Holdings Ltd • Cambridge

Hybrid
GBP 90,000 - 120,000
Competitive salary
Pension
Professional development
+2
GPU Kernel and Performance Engineer
GPU Kernel and Performance Engineer

CommonAI Holdings Ltd • Cambridge

Hybrid
GBP 90,000 - 120,000
Competitive salary
Pension
Professional development
+2
GPU Kernel and Performance Engineer
GPU Kernel and Performance Engineer

CommonAI C.I.C. • Cambridge

On-site
GBP 120,000 - 170,000
Competitive salary
Pension
Professional development
+1
Gpu Kernel And Performance Engineer
Gpu Kernel And Performance Engineer

Commonai C.I.C. • Cambourne

On-site
GBP 90,000 - 130,000
Competitive salary
Pension
Professional development
+2
Next-Gen GPU Performance Modeling Architect
Next-Gen GPU Performance Modeling Architect

Apple Inc. • Manor Park

On-site
GBP 90,000 - 130,000
AI Training GPU Performance Engineer
AI Training GPU Performance Engineer

present of AI • Cambridge

Remote
GBP 55,000 - 90,000
ML Performance & Kernel Engineer
ML Performance & Kernel Engineer

Recursive Superintelligence • Greater London

On-site
GBP 90,000 - 130,000
Senior ML Engineer, GPU Optimization for Open Models
Senior ML Engineer, GPU Optimization for Open Models

Boltz • Greater London

Hybrid
GBP 90,000 - 120,000
Equity
Hybrid work
GPU Modeling & Performance Engineer
GPU Modeling & Performance Engineer

Apple, Inc. • Cambridge

On-site
GBP 125,000 - 221,000
Stock options
Relocation assistance
Education reimbursement
+1