AI Inference Optimizations Engineer (MLIR/LLVM)

microTECH Global Limited; City of Edinburgh; Hybrid; GBP 90,000 - 120,000; Full time

Job summary

microTECH Global Limited in the United Kingdom is seeking an AI Compiler Optimization Engineer to push inference performance on CPU and hybrid CPU/XPU systems. You will implement advanced compiler techniques and profiling to uncover optimization opportunities.

You will profile frameworks such as TensorFlow, PyTorch, ONNX, and llama.cpp, propose kernel and graph-level optimizations, and contribute insights from industry research through technical reports.

Qualifications

• Experience with compiler optimizations for AI workloads.
• Familiar with MLIR/LLVM and JIT graph optimizations.
• Experience profiling AI frameworks and identifying bottlenecks.

Responsibilities

• Implement compiler techniques to enhance inference performance on CPU and CPU/XPU hybrid systems.
• Profile and optimize end-to-end inference workflows across AI frameworks.
• Track AI/compiler research and publish actionable insights.

Skills

Compiler optimizations

MLIR development

LLVM backend

Performance profiling

JIT optimization

Tools

LLVM

MLIR

TensorFlow

PyTorch

ONNX

llama.cpp

Job description

microTECH Global Limited in the United Kingdom is seeking an AI Compiler Optimization Engineer to push inference performance on CPU and hybrid CPU/XPU systems. You will implement advanced compiler techniques and profiling to uncover optimization opportunities.

You will profile frameworks such as TensorFlow, PyTorch, ONNX, and llama.cpp, propose kernel and graph-level optimizations, and contribute insights from industry research through technical reports.