Performance Engineer (Junior) AI Infrastructure Cambridge (Hybrid)

Pure Resourcing Solutions Limited; Cambridgeshire and Peterborough; Hybrid; GBP 42,000 - 70,000; Full time

Benefits offered by this job

Pension

Hybrid from Cambridge office

Job summary

Pure Resourcing Solutions Limited is recruiting a Performance Engineer (Junior) for Cambridge (Hybrid) up to 70k. You will work with senior engineers to build models predicting hardware performance from live training/inference metrics and turn data into actionable forecasts.

The role suits a strong academic with hands-on modeling, profiling, and Python data skills. The position offers hybrid work from Cambridge, exposure to AI infrastructure challenges, and the chance to influence decisions

Qualifications

• Postgraduate research background; PhD strongly preferred, exceptional master's graduates considered
• Solid grasp of computer architecture fundamentals and how LLMs run on hardware
• Experience building performance models or forecasting tools from research or projects
• Hands-on GPU/accelerator code experience (CUDA or equivalent)
• Familiarity with profiling and monitoring stacks (Nsight, PyTorch Profiler; Prometheus, Grafana)
• Strong Python for data work; Pandas and NumPy

Responsibilities

• Build and validate performance models from live training/inference metrics
• Turn metrics into calculators to answer whether to ship a change and cost implications
• Work with senior engineers for ownership and rapid iteration
• Contribute to monitoring and profiling workflows to improve hardware efficiency

Skills

PhD in CS

Computer architecture

LLMs on hardware

Performance modeling

Python data work

GPU/CUDA

Profiling tools

Monitoring stacks

Pandas & NumPy

Education

PhD in CS/Math/Physics

Tools

Nsight

PyTorch Profiler

Prometheus

Grafana

Job description

Performance Engineer (Junior) AI Infrastructure Cambridge (Hybrid) up to 70k

Most engineers find out whether a change works after it ships. This role is about knowing before anyone spends a penny on new hardware, building the models that predict it

My client is a Cambridge-based non-profit built on a fairly simple premise: different bits of the AI world keep solving the same infrastructure problems separately, and that's wasteful. So they've built a shared space where startups, big enterprises, government bodies and university researchers can pool that hard technical work instead. Early days as an organisation, but real backing and real momentum behind it.

This particular seat is for an early career professional. We're after someone academically exceptional, ideally with a PhD, who's ready to get stuck into real technical work quickly rather than needing a long runway to get there.

You'd work alongside senior engineers on the team, pulling real metrics off live training and inference jobs and turning them into models and calculators that answer actual questions, whether an optimisation is worth shipping, whether a different setup would run cheaper. Real ownership early, with senior support close by.

What you'll bring

• A postgraduate research background, ideally a PhD in computer science, mathematics, physics or a closely related field, strongly preferred, exceptional recent master's graduates with directly relevant coursework will also be considered
• A genuine, demonstrated grasp of computer architecture fundamentals and how LLMs and deep learning models actually run on hardware, training versus inference, matrix multiplication, KV-caching
• Real experience building performance models or forecasting tools, Python or spreadsheet-based, from research, a thesis, a placement, or serious personal projects
• Hands-on work with GPU or accelerator code, CUDA or similar
• Familiarity with profiling tools (Nsight, PyTorch Profiler) and ideally some exposure to monitoring stacks (Prometheus, Grafana)
• Strong Python for data work, Pandas and NumPy, genuine scripting ability

Nice to have: exposure to inference serving frameworks like vLLM, published research, or open source contributions in this space.

Why look twice at this one

An early route into industry for someone whose academic record speaks for itself, working directly with senior engineers on problems with real backing behind them. Pension, hybrid from a Cambridge office, and exposure to people across the wider AI and academic scene most people this early in their career don't get.