About the Role
We’re looking for experienced software engineers to help develop ExecuTorch, PyTorch’s framework for running AI models efficiently on edge devices.
You’ll join a team building software across AI model optimisation, compilers, runtimes and hardware acceleration. Our technology spans Python developer tools and ahead-of-time compilation through to portable C++ runtimes and hardware-accelerated backends, giving you the opportunity to contribute at different layers of the software stack.
A key part of this role is understanding how AI models execute on hardware, identifying bottlenecks and improving cycle count, latency, memory use and power efficiency.
You’ll move between high-level model transformations and low-level runtime and hardware behaviour to solve complex performance problems.
ExecuTorch targets Arm technology including Mali GPUs with Neural Graphics, Cortex-A and Cortex-M CPUs, and Ethos-U NPUs. We contribute to ExecuTorch in the open and work with the wider PyTorch community to help developers deploy AI models efficiently across mobile, embedded and other resource-constrained platforms.
What You’ll Do
- Develop and optimise components of the ExecuTorch compiler, runtime and developer tooling, ranging from Python APIs and model transformations to low-level C and C++ components.
- Analyse and profile AI workloads to identify bottlenecks, improving latency, memory use, cycle count and power efficiency across model transformations, generated code, runtimes and hardware backends.
- Develop optimised backends for Mali GPUs, Cortex-A and Cortex-M CPUs, Ethos-U NPUs and other edge platforms, while investigating software and performance challenges across the stack.
- Identify technical opportunities and take solutions from initial idea through delivery, working with engineers across Arm and contributors in the PyTorch open-source community.
- Share technical knowledge and, depending on your experience, contribute to technical projects and mentor other engineers.
What We’re Looking For
We’re looking for professional software engineering experience using C++ and Python, including developing, debugging and maintaining production-quality software.
You’ll have knowledge of programming, compilers, runtimes or performance optimisation, along with an interest in understanding how software executes on hardware and how its efficiency can be improved. An interest in AI and deploying models on resource-constrained devices will also be valuable.
You should be able to identify technical problems, determine a practical approach and take work through to completion. The role also requires good communication, technical judgement and the ability to work effectively with engineers across different teams.
You don’t need to meet every preferred qualification. AI and edge computing are evolving quickly, and relevant experience can come from different technical areas. If you’re keen to develop your knowledge and tackle new technical challenges, we’d like to hear from you!
Useful Additional Experience
Experience with PyTorch, ExecuTorch or another machine-learning framework would be useful, as would knowledge of ahead-of-time compilers, graph transformation or model optimisation. We’re also interested in experience with embedded systems, mobile or edge computing, hardware-accelerator programming, performance analysis, Vulkan, open-source development, technical leadership or mentoring.
Why Join the Team?
Help develop open-source AI technology used by developers around the world! You’ll have opportunities to build expertise across AI software, compilers, runtimes and edge computing while solving problems that connect software directly with the underlying hardware.
The breadth of the role allows you to explore both high-level AI frameworks and low-level hardware optimisation, improving performance and power efficiency across a wide range of edge devices. You’ll also work with specialists across Arm and the wider PyTorch ecosystem, with opportunities to develop and share your technical expertise.
We support different needs and ways of working. If you need reasonable accommodations during the recruitment process, please let us know and we’ll work with you to provide the support you need.
Please note that no relocation package is available for this role.
#LI-CM1
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.