Senior ML Inference & Compiler Engineer

NVIDIA Corporation; Cambridge; Hybrid; GBP 95,000 - 135,000; Full time

Job summary

NVIDIA Corporation seeks engineers to develop algorithms and optimizations for LPX inference and compiler stack. You will map neural network workloads onto NVIDIA platforms, integrating with NVIDIA's software ecosystem and libraries.

Ideal candidates have strong systems programming skills (C/C++/Rust), experience with LLVM/MLIR, and familiarity with TensorFlow, PyTorch, and ONNX. Hybrid work model in Cambridge, UK is offered.

Qualifications

• MS or PhD in Computer Science, Electrical/Computer Engineering, or related field, or equivalent experience.
• 6 years of relevant experience.
• Strong software engineering with systems-level programming (C/C++, Rust).
• Experience with compiler/runtime development, IR design, optimization passes, or code generation.
• Experience with LLVM and/or MLIR, including building passes, dialects, or integrations.
• Familiarity with TensorFlow, PyTorch, and ONNX for graph formats.

Responsibilities

• Build and maintain high-performance runtime and compiler components for end-to-end inference optimization.
• Define mappings of large-scale inference workloads onto NVIDIA systems.
• Extend and integrate with NVIDIA SW ecosystem through libraries, tooling, and interfaces.
• Benchmark, profile, and optimize mappings to ensure efficient neural network graphs mapping to hardware.
• Collaborate with hardware architects to feedback software observations and influence future architectures.
• Prototype and evaluate new compilation/runtime techniques, including graph transformations and memory/layout optimizations for spatial processors.
• Publish and present work on compilation approaches at ML/CC venues.

Skills

C/C++

Rust

LLVM/MLIR

TensorFlow

PyTorch

ONNX

Concurrency

Profiling

System programming

Education

MS or PhD in CS/EE or related field

Tools

LLVM

MLIR

ONNX

Job description

NVIDIA Corporation seeks engineers to develop algorithms and optimizations for LPX inference and compiler stack. You will map neural network workloads onto NVIDIA platforms, integrating with NVIDIA's software ecosystem and libraries.

Ideal candidates have strong systems programming skills (C/C++/Rust), experience with LLVM/MLIR, and familiarity with TensorFlow, PyTorch, and ONNX. Hybrid work model in Cambridge, UK is offered.