Are you interested in the next wave of AI applications for edge devices? Do you enjoy optimizing AI workloads and solving real world challenges?
We are looking for an experienced engineer with a background in AI inference optimisation to analyse, optimise and influence Arm IP and tooling for edge AI compute. You will be part of a growing team investigating emerging use-cases for edge AI , including large models and workloads not usually found in edge devices today.
Position is based in Cambridge, UK.
Job Overview:
As a senior member of the engineering team you will lead inference performance analysis investigations, producing data-led analysis and conclusions which help define requirements for future edge AI solutions.
You will bring expertise in AI optimisation tools and techniques, with experience solving runtime performance challenges and targeting CPU/GPU or NPU style architectures.
You will use your knowledge of optimisation techniques and underlying compute architectures to build a deep understanding of critical use cases. You will look at how workloads utilise available compute and memory resources, how targeting different compute resources affects performance and the effectiveness of different optimisation strategies.

Responsibilities:

• Development, de-composition and characterisation of AI workloads based on complex real world use-cases
• Optimisation of workloads for representative and real customer workloads, extending the frontier of edge AI deployment capability
• Production of reliable, robust research and analytics to inform future engineering and technology requirements, targeting a range of processor architectures
• Influencing user requirements for AI runtime software and tooling, in order to improve customer experiences of Arm products
• Helping to grow the team and train others in the art of inference performance optimisation and toolchains

Required Skills and Experience :

• University degree (or equivalent) in Computer Science, Engineering or scientific discipline
• Practical knowledge of factors which influence AI inference performance
• Software development experience relevant to workload analysis and optimisation in languages such as Python and C++
• Experience with AI inference runtime environments such as ONNX Runtime, TensorRT, TensorFlow Lite or ExecuTorch
• Knowledge of underlying DNN structures such as CNN, LSTM, Self Attention
• Good interpersonal skills and confidence explaining complex results to non technical audiences
• Experience in coaching or mentoring others

“Nice To Have” Skills and Experience :

• Experience compressing models for edge AI devices
• Delivery of AI workloads into edge AI products

In Return:
You will be provided with the training and environment to succeed in this role. As well as a friendly and high-performance working environment. We are offering a hybrid approach to home and office working to provide an adaptable experience for all employees and to promote a strong collaborative environment.
Accommodations at Arm
At Arm, we want to build extraordinary teams. If you need an adjustment or an accommodation during the recruitment process, please email accommodations@arm.com. To note, by sending us the requested information, you consent to its use by Arm to arrange for appropriate accommodations. All accommodation or adjustment requests will be treated with confidentiality, and information concerning these requests will only be disclosed as necessary to provide the accommodation. Although this is not an exhaustive list, examples of support include breaks between interviews, having documents read aloud, or office accessibility. Please email us about anything we can do to accommodate you during the recruitment process.
Hybrid Working at Arm
Arm’s approach to hybrid working is designed to create a working environment that supports both high performance and personal wellbeing. We believe in bringing people together face to face to enable us to work at pace, whilst recognizing the value of flexibility. Within that framework, we empower groups/teams to determine their own hybrid working patterns, depending on the work and the team’s needs. Details of what this means for each role will be shared upon application. In some cases, the flexibility we can offer is limited by local legal, regulatory, tax, or other considerations, and where this is the case, we will collaborate with you to find the best solution. Please talk to us to find out more about what this could look like for you.
Equal Opportunities at Arm
Arm is an equal opportunity employer, committed to providing an environment of mutual respect where equal opportunities are available to all applicants and colleagues. We are a diverse organization of dedicated and innovative individuals, and don’t discriminate on the basis of race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or status as a protected veteran

• Development, de-composition and characterisation of AI workloads based on complex real world use-cases
• Optimisation of workloads for representative and real customer workloads, extending the frontier of edge AI deployment capability
• Production of reliable, robust research and analytics to inform future engineering and technology requirements, targeting a range of processor architectures
• Influencing user requirements for AI runtime software and tooling, in order to improve customer experiences of Arm products
• Helping to grow the team and train others in the art of inference performance optimisation and toolchain