Overview
Job Overview
At Arm, we develop technology that enables AI and applications to run across billions of devices worldwide, from cloud to edge.
We are looking for an AI Software Engineer to optimize AI frameworks and enable efficient model deployment on Arm-based platforms. This role combines machine learning, systems engineering, and developer enablement, helping partners bring AI applications to edge, mobile, and other computing environments.
You will work hands-on with model optimization, framework and runtime integration, and cross-platform validation. Working closely with partners and Arm engineering teams, you will enable early adoption of emerging Arm technologies, including through virtual and pre-silicon platforms where appropriate.
Your analysis of application performance and system behavior will help improve Arm software, tools, and future hardware, while reusable demonstrations and technical guidance will support broader ecosystem adoption.
Key Responsibilities
- Enable partner and open-source AI models and applications on Arm-based platforms through framework, runtime, and SDK integration.
- Optimize model execution through techniques such as quantization, graph optimization, operator fusion, tiling, and memory optimization.
- Profile and debug workloads across applications, frameworks, runtimes, and hardware interfaces to identify performance and compatibility issues.
- Build reproducible workflows for cross-platform validation and benchmarking, assessing accuracy, latency, throughput, memory usage, and power efficiency where measurable.
- Collaborate with partners and internal teams to enable emerging Arm technologies, resolve adoption challenges, and share findings through demos, technical guides, and engineering reports.
Necessary Skills and Experience
- Strong software engineering experience in AI deployment, inference frameworks, runtimes, or performance optimization.
- Practical understanding of neural networks, including transformer-based models or CNNs, and experience optimizing models for resource-constrained devices.
- Hands-on experience with AI frameworks and deployment tools such as PyTorch, ONNX Runtime, LiteRT, ExecuTorch, or vendor-specific SDKs.
- Strong Python and C/C++ skills, with experience developing and debugging software on Linux or Android.
- Experience profiling AI workloads across software layers, identifying bottlenecks, and validating optimization results against accuracy and performance baselines.
- Strong analytical, communication, and documentation skills, with the flexibility to work across partner applications and collaborate with external engineering teams.
Preferred Skills and Background
- Experience with Arm architecture, Arm AI software tools, or optimization for CPUs, NPUs, and other accelerators.
- Understanding of hardware and system performance, including compute utilization, memory bandwidth, interconnects, and thermal constraints.
- Experience with model compression, pruning, LoRA/PEFT, or low-level kernel and inference-backend optimization.
- Familiarity with automotive or robotics AI applications, embedded systems, or virtual and pre-silicon development environments.
- Contributions to open-source frameworks or developer ecosystems through code, technical publications, tutorials, or demonstrations.
Education
A bachelor’s or master’s degree in Computer Science, Computer Engineering, Electrical Engineering, Machine Learning, or a related field, or equivalent practical experience.#LI-SL1