AI-Driven CPU Microarchitecture Research Engineer

Huawei; Cambridge; On-site; GBP 85,000 - 130,000; Full time

Job summary

Huawei R&D UK (Cambridge) is seeking an ambitious Research Engineer to work at the intersection of machine learning and CPU microarchitecture on the Kirin CPU Team. You will use reinforcement learning, LLM agents and learned models to discover and validate improvements for next-generation out-of-order CPU cores, including agentic systems that turn research papers into simulated, measured results.

This role suits someone early in their career who is fluent with cycle-accurate simulators and

Qualifications

• Solid understanding of out-of-order CPU microarchitecture including speculative execution and memory hierarchy.
• Hands-on depth in two of: architectural/simulation, RL/model training, LLM agent systems, compilers or performance kernels.

Responsibilities

• Build RL, Bayesian and LLM-agent-driven design-space exploration over gem5 and cycle-accurate models, using fast simulation for broad search and detailed models to validate candidates.
• Develop agentic pipelines that read architecture papers and implement mechanisms in simulators, run experiments and verify results including reward design and checks.
• Train surrogate and ML performance models that predict IPC and PPA impact and reduce simulation cost.
• Characterise workloads on CPUs (on-device LLM inference, matrix/vector extensions, KV-cache) and translate findings into microarchitecture proposals.
• Attribute bottlenecks as hardware-fixable, software-fixable or joint, and work with compiler/runtime/kernel engineers on co-design solutions.
• Turn strong results into patents, internal reports and, where appropriate, publications.

Skills

C++

Python

Reinforcement learning

LLM agents

Education

PhD (completed or in progress)

Tools

gem5

ChampSim

LLVM/MLIR

CUDA

Job description

Huawei R&D UK (Cambridge) is seeking an ambitious Research Engineer to work at the intersection of machine learning and CPU microarchitecture on the Kirin CPU Team. You will use reinforcement learning, LLM agents and learned models to discover and validate improvements for next-generation out-of-order CPU cores, including agentic systems that turn research papers into simulated, measured results.

This role suits someone early in their career who is fluent with cycle-accurate simulators and