Senior ML Inference & Compiler Architect

NVIDIA Corporation

Cambourne

Hybrid

GBP 90,000 - 140,000

Full time

11 days ago

Get a reply from this employer

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

Get past ATS filters

Job summary

NVIDIA Corporation in Cambourne, United Kingdom, is seeking engineers to develop algorithms and optimizations for inference and compiler stacks. You will work at the intersection of large-scale systems, compilers, and deep learning to map neural network workloads onto NVIDIA platforms.

Ideal candidates hold an MS or PhD in CS/EE with 5+ years of experience, strong systems programming skills in C/C++/Rust, and hands-on experience with LLVM/MLIR, ML frameworks, and graph-based IR workloads.

Qualifications

  • MS or PhD in CS/EE or equivalent with 5+ years of relevant experience.
  • Strong systems programming skills in C/C++ and/or Rust.
  • Hands-on with compiler/runtime development, IR design, and code generation.
  • Experience with LLVM/MLIR, including passes, dialects, or integrations.
  • Experience with ML frameworks (TensorFlow, PyTorch) and ONNX.
  • Familiarity with GPUs and spatial accelerators.
  • Excellent collaboration and communication across teams.

Responsibilities

  • Build and maintain high-performance runtime and compiler components for inference optimization.
  • Define mappings of large-scale inference workloads onto NVIDIA systems.
  • Integrate with NVIDIA SW ecosystem, libraries, tooling, and interfaces.
  • Benchmark and profile performance to ensure efficient code generation for NN graphs.
  • Collaborate with hardware teams to feed observations and influence architectures.
  • Prototype new compilation and runtime techniques for graph transforms and memory layouts.
  • Publish and present work at ML, compiler, and architecture venues.

Skills

Systems programming
Algorithms & data structures
Parallel computing
Debugging & profiling
Cross-team collaboration

Education

MS or PhD in CS/EE

Tools

LLVM/MLIR
ONNX
TensorFlow
PyTorch

Job description

NVIDIA Corporation in Cambourne, United Kingdom, is seeking engineers to develop algorithms and optimizations for inference and compiler stacks. You will work at the intersection of large-scale systems, compilers, and deep learning to map neural network workloads onto NVIDIA platforms.

Ideal candidates hold an MS or PhD in CS/EE with 5+ years of experience, strong systems programming skills in C/C++/Rust, and hands-on experience with LLVM/MLIR, ML frameworks, and graph-based IR workloads.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Senior ML Inference & Compiler Engineer
Senior ML Inference & Compiler Engineer

NVIDIA Corporation • Cambourne

Hybrid
GBP 110,000 - 150,000
Senior Machine Learning Applications And Compiler Engineer
Senior Machine Learning Applications And Compiler Engineer

NVIDIA Corporation • Cambourne

Hybrid
GBP 90,000 - 140,000
AI Compiler Engineer: MLIR & GPU Inference
AI Compiler Engineer: MLIR & GPU Inference

NVIDIA Corporation • United Kingdom

Remote
GBP 95,000 - 125,000
Senior ML Inference & Compiler Engineer (LPX)
Senior ML Inference & Compiler Engineer (LPX)

NVIDIA Corporation • United Kingdom

On-site
GBP 90,000 - 130,000
Senior Machine Learning Applications And Compiler Engineer, Lpx
Senior Machine Learning Applications And Compiler Engineer, Lpx

NVIDIA Corporation • Cambourne

Hybrid
GBP 110,000 - 150,000
Senior Machine Learning Applications and Compiler Engineer, LPX
Senior Machine Learning Applications and Compiler Engineer, LPX

NVIDIA Corporation • United Kingdom

On-site
GBP 60,000 - 90,000
AI Compiler Engineer: Kernel Gen & MLIR Innovation
AI Compiler Engineer: Kernel Gen & MLIR Innovation

NVIDIA Corporation • Cambridge

On-site
GBP 110,000 - 160,000
Compiler Engineer - AI Inference
Compiler Engineer - AI Inference

NVIDIA Corporation • Cambridge

On-site
GBP 110,000 - 160,000
Compiler Engineer - Ai Inference
Compiler Engineer - Ai Inference

NVIDIA Corporation • Cambourne

On-site
GBP 80,000 - 140,000
Compiler Engineer - AI Inference
Compiler Engineer - AI Inference

NVIDIA Corporation • United Kingdom

Remote
GBP 95,000 - 125,000