Overview
We are seeking a skilled AI Compiler Optimization Engineer to optimize AI model inference performance through advanced compiler technologies. You will focus on performance tuning for CPU or hybrid CPU/XPU heterogeneous architectures, profile AI frameworks to discover new optimization opportunities, and deliver cutting-edge insights from industry research.
Responsibilities
* Compiler-Based Performance Optimization: Implement compiler techniques (e.g., MLIR level optimizations, LLVM backend optimizations) to enhance inference performance on CPU and CPU/XPU hybrid systems.
* Optimize JIT level compute graphs with operator fusion, memory allocation and other optimizations for latency and throughput improvements.
* Proposed: Experience with LLVM/MLIR development.
* AI Model Profiling & Framework Optimization: Profile end-to-end inference workflows on frameworks like TensorFlow, PyTorch, ONNX, and llama.cpp to identify hotspots and bottlenecks.
* Propose and implement optimization strategies (e.g., kernel tuning, graph-level optimizations).
* Proposed: Experience optimizing models on multiple AI frameworks.
* Research & Insight Development: Track and analyze the latest advancements in AI and compiler research (academic papers, open-source projects).
* Produce actionable insight reports summarizing trends, benchmarks, and potential optimizations.
* Proposed: Strong technical writing skills with prior publications or reports.
Contract & Benefits
* Fixed term employment contract up to two years
* Flexible working
* 33 days annual leave entitlement per year (including UK public holidays)
* Group Personal Pension
* Corporate retail discounts
* Employee Assistance Programme
* Life insurance
* Corporate social events
About the Employer
This role is associated with Huawei Research and Development UK Limited. Huawei is a global provider of information and communications technology (ICT) infrastructure and smart devices. The company emphasizes innovation, collaboration with academic institutions, and a commitment to building a fully connected, intelligent world. The UK presence includes design centers in Cambridge, London, Edinburgh and Ipswich.
#J-18808-Ljbffr