AI Infrastructure Performance Engineer — Hybrid, High Impact

CommonAI CIC; Cambridge; Hybrid; GBP 52,000 - 78,000; Full time

Benefits offered by this job

Collaborative environment

Opportunity to impact UK AI capability

Competitive salary package

Job summary

CommonAI CIC is seeking a hardware-software performance engineer to design and run reproducible experiments that reveal how AI infrastructure behaves. You will build measurement tools and collect traces across hardware and software stacks, shaping data to support SIL's simulation platform and investment decisions.

Collaboration with workload, simulation and uncertainty specialists will help identify bottlenecks, explain performance variation, and calibrate models.

Qualifications

• Experience investigating the performance of real computing systems and designing experiments that support rigorous conclusions.
• Depth in accelerator profiling, inference runtimes, memory systems, distributed/HPC workloads, networking, or power and energy measurement.
• The ability to build maintainable automation and analysis tools in a suitable software language, and to learn unfamiliar profiling tools.
• Knowledge and care of experimental controls, repeatability, confounding effects and the limits of a measurement.
• Some experience using AI coding agents, alongside sound debugging and review habits.

Responsibilities

• Design and run reproducible experiments, from individual hardware or software components to complete LLM serving systems, covering relevant workloads, configurations and operating conditions.
• Develop reusable measurement tools and collect traces, profiles and counters to characterise latency, throughput, memory behaviour and, where reliable measurement is possible, power and energy.
• Investigate bottlenecks, performance variation and unexpected behaviour across the layers your expertise covers, working with colleagues to extend the investigation through the stack.
• Take responsibility for reproducible workload details, software versions, configuration and measurement methods so results can be reproduced, compared and used to calibrate simulator models.
• Work with simulation and uncertainty specialists to choose measurements that resolve important unknowns and undertake curation of calibration and validation data.
• Help define the controls needed for experiments and use the resulting cluster-control interfaces, coordinating access and changes with colleagues responsible for the hardware.

Skills

Experiment design

Performance analysis

Automation tooling

Experimental controls

AI coding agents

Tools

Nsight

PyTorch Profiler

Job description

CommonAI CIC is seeking a hardware-software performance engineer to design and run reproducible experiments that reveal how AI infrastructure behaves. You will build measurement tools and collect traces across hardware and software stacks, shaping data to support SIL's simulation platform and investment decisions.

Collaboration with workload, simulation and uncertainty specialists will help identify bottlenecks, explain performance variation, and calibrate models.