1 day ago
Shanghai, ChinaSenior
Responsibilities
- Optimize and deploy neural-network and foundation models for efficient execution on Arm-based edge, mobile, and cloud hardware.
- Apply tiling, quantization, pruning, LoRA/PEFT, and other model optimization techniques.
- Profile and analyze full software stacks from application usage through runtimes, tooling, system architecture, and silicon readiness.
- Integrate Arm-based AI technologies with developer applications, ML frameworks, SDKs, and runtimes.
- Identify friction in developer tools and advocate for improvements in on-device inference and model deployment.
- Create technical guides, tutorials, benchmarks, performance analyses, white papers, blogs, talks, demos, and open-source contributions.
- Collaborate with engineering, product, ML framework, and tooling ecosystem teams to improve production readiness and developer adoption.
Requirements
- Strong problem-solving, debugging, profiling, systems analysis, and technical communication skills.
- Understanding of neural networks, including LLMs and CNNs, and efficient on-device AI model deployment.
- Experience with model optimization techniques and tools such as tiling, quantization, pruning, and LoRA/PEFT.
- Familiarity with ML frameworks including PyTorch, LiteRT, TensorRT, and Core ML.
- Strong experience with Python, embedded systems, and C/C++ across mobile Android and cloud/server Linux environments.
- Ability to explain sophisticated systems to varied audiences and contribute high-quality technical content.
- Preferred experience with automotive or robotics software, Android Automotive, IVI, ADAS, hardware and system architectures, CPUs, NPUs, accelerators, edge-to-cloud applications, ONNX, TFLite, containers, Kubernetes, and serverless infrastructure.
Benefits
- Hybrid working patterns are determined by the team, with role-specific details shared during the application process.
- Work arrangements may be subject to local legal, regulatory, tax, or other considerations.
- Recruitment accommodations are available upon request and are handled confidentially.
Tech Stack
Categories
About Arm
Arm’s foundational technology is defining the future of computing. A future built by the greatest technology ecosystem in the world. A future built on Arm. Arm is everywhere technology matters. Technology matters everywhere. Together, we’ll power every technology revolution moving forward, including cloud computing, automotive and autonomous systems, IoT, the metaverse, and beyond. Changing the world. Again. On Arm.