2 months ago
Shanghai, China or Shenzhen, ChinaSenior
Responsibilities
- Optimize neural networks and foundation models for efficient on-device and edge deployment using tiling, quantization, pruning, and LoRA/PEFT.
- Integrate Arm-based AI technologies with developers’ applications, ML frameworks, runtimes, and tooling to improve performance and production readiness.
- Profile, debug, and analyze complete software stacks from application usage through system architecture on mobile, edge, and cloud platforms.
- Identify friction in SDKs, runtimes, tooling, and silicon and advocate for improvements with engineering and product teams.
- Develop technical guides, tutorials, benchmarks, performance analyses, white papers, blogs, talks, demos, and open-source contributions.
- Enable influential AI applications on Arm technologies before market release and provide system-level insights for future products.
Requirements
- Strong problem-solving, debugging, profiling, systems analysis, and technical communication skills.
- Understanding of neural networks such as LLMs and CNNs and experience deploying efficient AI models on devices.
- Familiarity with ML frameworks and tooling such as PyTorch, LiteRT, TensorRT, and Core ML.
- Strong experience with Python, embedded software, and C/C++.
- Experience analyzing full software stacks on Arm-based devices from Android mobile systems to Linux cloud servers.
- Passion and flexibility for working across varied third-party AI applications.
- Preferred experience with automotive or robotics software, Android Automotive, IVI, or ADAS.
- Preferred understanding of compute, memory, PCIe, mesh, and thermal hardware and system architectures.
- Preferred systems-level performance optimization experience on CPUs, NPUs, and accelerators.
- Preferred experience with edge-to-cloud applications, model formats and optimization such as ONNX and TFLite, and cloud infrastructure such as containers, Kubernetes, and serverless systems.
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.