Power and Performance Engineer, PAI Platforms and Performance Analysis

Power and Performance Engineer, PAI Platforms and Performance Analysis Overview

Arm is seeking a practical, hands-on Power and Performance Engineer to join its Platforms and Performance Analysis group. This position is centered on analysing the power and performance behavior of system-on-chip platforms, with work spanning both pre-silicon and post-silicon methodology. The role also includes defining thermal design power approaches, automating workload execution and measurement, and helping shape product requirements for PAI offerings aimed at robotics and automotive markets.

The successful candidate will work closely with hardware and software, running workloads on Linux-based devices and development platforms, studying how systems behave under load, and turning those observations into recommendations that influence architecture, product direction, software choices, and platform strategy.

What you will do

• Perform detailed, practical profiling of SoC power and performance across major compute and system components, including CPUs, GPUs, NPUs or AI accelerators, memory subsystems, interconnects, and full-system workloads.
• Execute benchmark suites and real-world workloads on Linux-based devices, development boards, reference platforms, and environments used before and after silicon is available.
• Design, build, and maintain automation frameworks that support workload execution, profiling, telemetry collection, power measurement, and analysis of results.
• Lead the methodology used for pre-silicon power and performance analysis, including workload selection, benchmark definition, estimation planning, and correlation strategy.
• Support post-silicon analysis by characterising platforms, identifying bottlenecks, and evaluating the balance between power consumption and performance delivery.
• Develop thermal design power methodology for SoC products, linking workload behavior to sustained performance, peak power, thermal constraints, and product segmentation.
• Define power and performance requirements for PAI products intended for robotics and automotive applications.
• Document findings clearly and provide technical recommendations to architecture, product, software, systems, and platform teams.

What you need

• Demonstrated experience in either pre-silicon or post-silicon power and performance analysis.
• Experience analysing SoC power and performance in heterogeneous compute environments, such as systems containing CPUs, GPUs, NPUs, memory, or interconnects.
• Practical experience running workloads on Linux-based hardware, development boards, embedded systems, or pre/post-silicon environments.
• Experience building or using automation harnesses for workload execution, data capture, profiling, and analysis.
• A solid understanding of the trade-offs between power, thermal behavior, and performance in complex SoCs.
• Familiarity with profiling tools, performance counters, system traces, telemetry sources, or power measurement equipment.
• Strong scripting and data analysis skills, for example using Python, shell scripting, or comparable tools.
• The ability to convert workload behavior and product use cases into measurable engineering requirements.
• Strong communication skills and the ability to explain technical trade-offs to engineering, architecture, and product partners.
• A degree in Electronics Engineering, Electrical Engineering, Computer Engineering, Computer Science, or equivalent industry experience.

Additional experience that would be helpful

• Background with embedded robotics development platforms.
• Experience in platform performance analysis, silicon validation, performance modelling, systems engineering, or architecture analysis.
• Exposure to automotive, robotics, edge AI, embedded AI, or heterogeneous compute platforms.
• Familiarity with AI and machine learning workloads, vision pipelines, robotics perception and planning workloads, or automotive ADAS workloads.
• Experience defining thermal design power, sustained performance targets, thermal constraints, or power envelope methodologies.
• Knowledge of Arm architecture, Arm-based SoC platforms, Linux performance tools, and embedded software ecosystems.
• Experience using tools such as perf, ftrace, trace-cmd, sysfs, procfs, vendor telemetry tools, or power analysers.
• Experience with benchmark automation, lab infrastructure, remote device farms, or CI-style workload execution.
• Familiarity with pre-silicon environments such as performance models, simulators, emulation, FPGA-based platforms, or virtual platforms.

Working style and environment

This role is based in Cambridge, United Kingdom, and the working model is hybrid. Arm’s approach to hybrid working is intended to support both strong performance and personal wellbeing. The company values bringing people together in person to work efficiently, while also preserving flexibility. Teams are given the ability to decide the hybrid pattern that best fits their work and needs, and the exact arrangement for this role will be explained during the application process. In some situations, local legal, regulatory, tax, or other constraints may limit flexibility, and Arm will work with candidates to find the best possible solution.

Compensation and support

The advertised salary range for this position is £80,100 to £108,300 per year.

Arm also provides support for candidates who need adjustments during recruitment. Examples include extra breaks between interviews, having documents read aloud, or help with office accessibility. Requests for accommodations are handled confidentially and used only to arrange the support needed during the hiring process.

Arm describes itself as an equal opportunity employer and says it is committed to a respectful environment where applicants and employees are treated fairly regardless of race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or veteran status.

The company also notes that it offers benefits designed for people working on complex technology challenges and building the future of computing.

How to apply

Applicants can submit their interest through the job application process on Arm’s careers site. The page also provides options to save the job, view the location, and access the hiring process information. If you need recruitment accommodations, you are encouraged to contact Arm at [email protected].

Arm also references its 10x mindset as a guide for how it engineers, collaborates, and develops talent, and directs candidates to its careers site for more information about that approach.

Degree Requirement: Not Specified

Visa Sponsorship Promising