LLM-driven Code Optimization Research Engineer (Contractor) in Cambridge

About Huawei Research and Development UK Limited

Founded in 1987, Huawei is a leading global provider of information and communications technology (ICT) infrastructure and smart devices. We have 207,000 employees and operate in over 170 countries and regions, serving more than three billion people around the world.

Our vision and mission is to bring digital to every person, home and organization for a fully connected, intelligent world. To this end, we will drive ubiquitous connectivity and promote equal access to networks; bring cloud and artificial intelligence to all four corners of the earth to provide superior computing power where you need it, when you need it; build digital platforms to help all industries and organizations become more agile, efficient, and dynamic; redefine user experience with AI, making it more personalized for people in all aspects of their life, whether they’re at home, in the office, or on the go.

This spirit of innovation has led Huawei to work in close partnership with leading academic institutions in the UK to develop and refine the latest technologies. With a shared commitment to innovation and progress, both parties have worked together to achieve common goals and establish a strong partnership. The partnership between UK and Huawei help to develop the technologies of the future that will transform the way we all communicate, work and live.

For the past 30 years we have maintained an unwavering focus, rejecting shortcuts and easy opportunities that don\’t align with our core business. With a practical approach to everything we do, we concentrate our efforts and invest patiently to drive technological breakthroughs.

This strategic focus is a reflection of our core values:

• staying customer-centric,
• inspiring dedication,
• persevering,
• Growing by reflection

Huawei Research and Development UK Limited Overview

Huawei’s vision is a fully connected, intelligent world. To achieve this, we work to inspire passion for basic research around the world. Our combined passion drives development across the global innovation value chain. Huawei has the largest Research and Development organization in the world with 96,000+ employees in research centers around the globe. In the UK, we already have design centers in Cambridge, London, Edinburgh and Ipswich. We continue to explore and define new research directions and new services. We have expanded our collaborations with academic researchers; researched new network architectures, integration of communications and key enabling technologies; and developed the fundamental theories of these technologies. We invite you to join us on this exciting journey and drive your career forward.

Job Purpose

Research and develop LLM-powered code optimization frameworks targeting HarmonyOS/OpenHarmony at scale. Design automated pipelines for function-level code analysis, transformation, and validation that deliver measurable IPC and system-wide performance improvements. Explore target-aware optimizations for device-specific builds and LLM-assisted architectural feature exploration using QEMU or GEM5 simulators.

Key Responsibilities

• Design and implement LLM-powered code optimization pipelines for large-scale HarmonyOS/OpenHarmony codebases, targeting ArkTS, ArkUI, and core system components.
• Develop automated profiling infrastructure to identify performance bottlenecks, costly functions, and critical code paths for optimization targeting.
• Research and implement LLM-driven code analysis and transformation techniques inspired by compiler optimization passes (loop unrolling, vectorization, memory access patterns).
• Build LLM-powered testing and validation frameworks that generate correctness tests, verify semantic equivalence, and benchmark performance improvements.
• Investigate target-aware code optimization techniques that specialize code for different device architectures, memory configurations, and hardware capabilities.
• Explore LLM-assisted architectural feature implementation and design space exploration using QEMU and GEM5 simulators.
• Develop methodologies to classify optimizations as trivial (compiler-achievable) versus architectural, and measure system-wide impact beyond microbenchmarks.

This job description is only an outline of the tasks, responsibilities and outcomes required of the role. The jobholder will carry out any other duties as may be reasonably required by his/her line manager. The job description and personal specification may be reviewed on an ongoing basis in accordance with the changing needs of Huawei Research and Development UK Limited.

Required

1. BSc degree in Computer Science, Machine Learning, Compiler Engineering, or related field with focus on code optimization, program synthesis, or LLM applications.

2. Experience with large language models for code-related tasks (code generation, code completion, program repair, or automated refactoring).

3. Some experience developing agentic systems.

4. Strong programming skills in C/C++ and Python.

5. Experience with performance profiling, benchmarking methodologies, and microarchitectural analysis tools.

6. Highly-motivated and independent individual with a strong desire for knowledge acquisition and research innovation.

Desired

• Experience with compiler frameworks (LLVM, GCC) or JIT systems.
• Some understanding of compiler optimization techniques, including loop transformations, vectorization, instruction scheduling, and register allocation.
• Experience with HarmonyOS/OpenHarmony, ArkTS, ArkUI frameworks or similar mobile operating system components.
• Knowledge of ARM architecture, instruction set, and microarchitectural optimization techniques.
• Experience with QEMU or GEM5 simulators for architectural exploration and design space analysis.
• Background in automated test generation, fuzzing, or formal verification for code correctness validation.
• Experience with LLM fine-tuning, prompt engineering, or building LLM-based agentic systems for software engineering tasks.
• Understanding of IPC analysis, pipeline stalls, cache behavior, and low-level performance optimization.
• Track record of technology transfer from research prototypes to production systems.

#J-18808-Ljbffr