Senior ML Inference & Compiler Engineer

NVIDIA; Cambridge; On-site; GBP 110,000 - 140,000; Full time

Job summary

NVIDIA is seeking engineers to develop algorithms and optimizations for our LPX inference and compiler stack in Cambridge. You will work at the intersection of large-scale systems, compilers, and deep learning, shaping how neural network workloads map onto NVIDIA platforms.

You’ll build high-performance runtime and compiler components, map workloads, and extend with NVIDIA’s software ecosystem. A strong CS/EE background with compiler, MLIR, and DL framework experience is required.

Qualifications

• MS or PhD in Computer Science, Electrical/Computer Engineering, or related field, or equivalent experience, with 6 years of relevant experience.
• Strong software engineering background with systems level programming (C/C++ and/or Rust) and solid CS fundamentals.
• Hands on experience with compiler or runtime development, including IR design, optimization passes, or code generation.
• Experience with LLVM and/or MLIR, including building custom passes, dialects, or integrations.
• Familiarity with deep learning frameworks such as TensorFlow and PyTorch, and experience with ONNX.
• Solid understanding of parallel and heterogeneous compute architectures (GPUs, spatial accelerators).
• Strong debugging and profiling skills with performance-driven mindset.
• Excellent communication and collaboration skills across hardware, systems, and software teams.
• Ideal candidates will have MLIR-based compiler or multilevel IR stack experience, especially for graph DL workloads.

Responsibilities

• Build and maintain high-performance runtime and compiler components for end-to-end inference optimization.
• Map large-scale inference workloads onto NVIDIA platforms.
• Extend with NVIDIA SW ecosystem, libraries, tooling, and interfaces for model deployment.
• Benchmark, profile, and monitor performance of compiled graphs on inference hardware.
• Collaborate with hardware teams to feed observations and influence future architectures.
• Prototype new compilation and runtime techniques, including graph transformations and scheduling.

Skills

C/C++

Rust

Data structures

Concurrency

Profiling

Communication

Teamwork

MLIR knowledge

Education

MS/PhD in CS/EE

Tools

LLVM

MLIR

ONNX

TensorFlow

PyTorch

Job description

NVIDIA is seeking engineers to develop algorithms and optimizations for our LPX inference and compiler stack in Cambridge. You will work at the intersection of large-scale systems, compilers, and deep learning, shaping how neural network workloads map onto NVIDIA platforms.

You’ll build high-performance runtime and compiler components, map workloads, and extend with NVIDIA’s software ecosystem. A strong CS/EE background with compiler, MLIR, and DL framework experience is required.