Senior Developer - Relations Engineer

At Arm, we're enabling AI and applications from the most influence developers in China to run everywhere-from cloud to edge -powering billions of devices worldwide!

This role sits at the intersection of machine learning, systems optimization, and developer experience, with a focus on enabling efficient deployment of AI models on Arm-based devices. You will work hands-on with model optimization techniques such as tiling, quantization, pruning etc. to help developers transform large foundation models into production-ready, resource-efficient versions that run locally on edge and mobile hardware. You will work on developer's applications based on standard software stacks and frameworks by integrating arm-based AI technologies to boost performance of their models and frameworks much earlier before the technologies go to market. You will do in-depth profiling and analysis of the whole solution stack all the way from application usage down to the architecture even before silicon is available to use. You'll work closely with engineering and product teams to identify friction in SDKs, runtimes, tooling or even silicon for app developer adoption of Arm technologies. You will advocate for improvements across areas like on-device inference, model deployment, etc. through high quality contents like white papers, talks, demos etc., in various developer events.

Success of this role means enablement of Arm AI technologies in highly influential AI applications before technologies go to market and equally important to drive in-depth insights based on analysis of the full system behavior to designer better future products.

What You'll Bring

• Strong problem solving and analysis skills. Articulate and clarity in technical issues and deliverables in reports or meetings. Ability to explain sophisticated systems to a range of audiences

• Understanding of neural network (e.g. LLM, CNN etc.) and deploy efficient AI models on device through optimization techniques and tools like tiling, quantization, pruning, and LoRA/PEFT etc.

• Familiarity with ML frameworks (e.g., Pytorch, LiteRT, TensorRT, Core ML) and partner with ML frameworks and tooling ecosystems to optimize runtimes and ensure production readiness.

• Develop technical guides, tutorials, and benchmarking and analysis reports focused on performance and efficiency on Arm platforms.

• Strong debugging, profiling and analysis skills of full software stacks on arm based devices: mobile (Android) to cloud (server/Linux). Strong experience in Python, Embedded, C/C++.

• Passion in the above areas and great flexibility to work on various AI applications from 3rd parties

• Contributions to developer ecosystems through high quality contents like white papers, blogs, talks, demos and open source engagements.

Preferences

• Experience with automotive/robotics software and applications like Android automotive, IVI or ADAS will be a big PLUS

• Understanding of hardware and system architectures (compute, memory, PCIe, mesh, thermal) in a big PLUS

• Systems-level understanding of performance optimization on CPUs, NPUs and accelerators.

• Experience with edge-to-cloud applications (mobile or IoT + cloud integration)

• Familiarity with model formats and optimization (e.g., ONNX, quantization, TFLite)

• Familiarity with modern cloud infrastructure (containers, Kubernetes, serverless)