Senior CPU/NPU Performance & Workload Modeling Expert

Huawei; Cambridge; On-site; GBP 120,000 - 180,000; Full time

Benefits offered by this job

33 days annual leave entitlement

Group Personal Pension

Life insurance

Private medical insurance

Medical expense claim scheme

Employee Assistance Program

Cycle to work scheme

Company sports club and social events

Additional time off for learning and发展

Job summary

Huawei in Cambridge seeks a senior performance engineer to lead workload modelling and simulation. You will design tools for architectural exploration, analyze CPU/NPU performance, and drive software/hardware co‑optimization for next‑generation processors.

The role requires deep experience in workload extraction, binary analysis, and high‑level modelling, with strong C++/Python skills and exposure to ML frameworks such as TensorFlow and PyTorch.

Qualifications

• Strong background in workload modelling and CPU/NPU Architecture.
• Experience with performance analysis and architectural exploration.
• Proficient in C++ and Python; knowledge of ML frameworks like TensorFlow, PyTorch.
• Experience with GEM5/Sniper or other performance simulators.
• Background in software/hardware co-optimization and binary analysis.

Responsibilities

• Plan and implement tool systems for architectural exploration and performance analysis.
• Drive software/hardware co-optimization features for next‑gen processors.
• Characterize and model complex workloads with high accuracy.
• Analyse real‑world workloads to support chip development decisions.

Skills

CPU/NPU Architecture

Workload Modelling

Performance Projection

C++

Python

TensorFlow

PyTorch

Binary Analysis

GEM5 (O3)

QEMU/DynamoRIO

CUDA/OpenCL

Tools

Sniper

DynamoRIO

GEM5

x86 PIN

Job description

Huawei in Cambridge seeks a senior performance engineer to lead workload modelling and simulation. You will design tools for architectural exploration, analyze CPU/NPU performance, and drive software/hardware co‑optimization for next‑generation processors.

The role requires deep experience in workload extraction, binary analysis, and high‑level modelling, with strong C++/Python skills and exposure to ML frameworks such as TensorFlow and PyTorch.