Senior ML Inference & Compiler Engineer (LPX)

NVIDIA Corporation; United Kingdom; Presencial; GBP 90.000 - 130.000; Jornada completa

Descripción de la vacante

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

Build, develop, and maintain high-performance runtime and compiler components, focusing on end-to-end inference optimization and efficient mappings.

Formación

• MS/PhD or equivalent; 6+ years in CS or EE.
• Expert in systems programming with C/C++ or Rust and strong CS fundamentals.
• Hands-on compiler/runtime development with IR design, optimization passes, or code generation.
• Experience with LLVM and MLIR, building custom passes or dialects.
• Familiar with TensorFlow, PyTorch, and ONNX graph formats.
• Strong understanding of GPUs, spatial accelerators, and heterogeneous architectures.
• Excellent debugging, profiling, and performance optimization skills.
• Excellent communication and collaboration across hardware, software teams.

Responsabilidades

• 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: libraries, tooling, interfaces.
• Benchmark, profile, and monitor performance to ensure efficient mappings.
• Collaborate with hardware teams to feedback software observations and influence architectures.
• Prototype and evaluate new compilation/runtime techniques for graph transforms and scheduling.
• Publish and present work at ML/Compiler/AC venues.

Conocimientos

C/C++

Rust

Data structures

Algorithms

Concurrency

Educación

MS/PhD in CS or EE

Herramientas

LLVM

MLIR

Descripción del empleo

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

Build, develop, and maintain high-performance runtime and compiler components, focusing on end-to-end inference optimization and efficient mappings.