Systems Performance Engineer, AI Infrastructure

CommonAI CIC

. Design and run reproducible experiments on hardware and software components through complete LLM serving systems .

Posted 10/23/2026full-timeCambridge • United KingdomMid-LevelSenior💰 £60,000 - £105,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in designing and running reproducible experiments on hardware and software components, with a focus on performance investigation and measurement in computing systems. Proficient in developing automation tools and analyzing experimental data to derive rigorous conclusions.

Highest-signal resume keywords

Performance InvestigationExperiment DesignAutomation Tool DevelopmentLLM Serving ExperienceProfiling Tools Familiarity

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Accelerator ProfilingInference RuntimesMemory SystemsDistributed WorkloadsHPC WorkloadsNetworkingPower MeasurementEnergy MeasurementDebuggingAnalysis Tools

Soft Skills

Attention to DetailCollaborationProblem-Solving

Tools & Technologies

NsightPyTorch ProfilerSystem ProfilersNetwork Profilers

Industry Keywords

Reproducible ExperimentsExperimental ControlsMeasurement MethodsCalibration DataValidation Data

Tech Stack

Tools & technologies

PyTorch

About the role

Key responsibilities & impact

Design and run reproducible experiments on hardware and software components through complete LLM serving systems
Cover relevant workloads, configurations and operating conditions
Develop reusable measurement tools
Collect traces, profiles and counters to characterize latency, throughput, memory behavior, power and energy where reliably measurable
Investigate bottlenecks, performance variation and unexpected behavior across the relevant stack layers
Maintain reproducible workload details, software versions, configurations and measurement methods
Work with simulation and uncertainty specialists to select measurements that resolve important unknowns
Curate calibration and validation data
Help define experiment controls and use cluster-control interfaces
Coordinate hardware access and changes with responsible colleagues
Establish reproducible reference experiments and measurement datasets

Requirements

What you’ll need

Experience investigating the performance of real computing systems and designing experiments that support rigorous conclusions
Depth in one or more relevant areas: accelerator profiling, inference runtimes, memory systems, distributed/HPC workloads, networking, or power and energy measurement
Ability to build maintainable automation and analysis tools in a suitable software language
Ability 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
LLM serving experience and familiarity with tools such as Nsight, PyTorch Profiler or system/network profilers would be useful, but are not required
Applicants across the UK are welcome
Relevant postgraduate study is useful, but qualifications are secondary to experience and quality of work

Benefits

Comp & perks

Help build UK AI capability and improve how investment and compute serve the public good
Build a network spanning UK hardware SMEs, major technology companies, venture and public investors, and leading universities
Shape a growing team with startup pace and close academic links
Use frontier models and coding agents with a substantial tooling budget
A collaborative and supportive work environment
The opportunity to have a high impact in a growing organisation
Competitive salary package, including pension and benefits
Professional development opportunities
Networking opportunities with influential figures from across the tech sector and academia
A vibrant office environment located a few minutes’ walk away from Cambridge train station
Hybrid working arrangement
Flexible part-time arrangements and consultancy options