Senior ML Inference & Compiler Engineer

NVIDIA; United Kingdom; On-site; GBP 60,000 - 90,000; Full time

Job summary

A leading technology firm in the UK is seeking engineers to develop algorithms and optimizations for their LPX inference and compiler stack. You will maintain high-performance components and collaborate closely with hardware teams to impact future architectures. Ideal candidates should have a strong software engineering background, proficiency in systems programming, and experience in compiler development. Join to contribute to cutting-edge technology and help shape the future of AI systems.

Qualifications

• 5 years of relevant experience in compiler or runtime development.
• Proficiency in data structures, algorithms, and concurrency.
• Solid understanding of performance profiling and benchmarking tools.

Responsibilities

• Develop algorithms and optimizations for LPX inference and compiler stack.
• Maintain high-performance runtime and compiler components.
• Collaborate with hardware architects for architecture feedback.
• Publish technical work on compilation approaches at major venues.

Skills

Systems level programming (C/C++ or Rust)

Compiler or runtime development

Deep learning frameworks (TensorFlow, PyTorch)

Parallel and heterogeneous compute architectures

Analytical and debugging skills

Education

MS or PhD in Computer Science or related field

Tools

LLVM

MLIR

Job description

A leading technology firm in the UK is seeking engineers to develop algorithms and optimizations for their LPX inference and compiler stack. You will maintain high-performance components and collaborate closely with hardware teams to impact future architectures. Ideal candidates should have a strong software engineering background, proficiency in systems programming, and experience in compiler development. Join to contribute to cutting-edge technology and help shape the future of AI systems.