- 地点
- 隆德，瑞典
- 类型
- 实习
职责
- 改进自动基准测试基础设施，以跟上不断涌现的新型尖端人工智能模型
- 开发用于查找编译器准确性的工具
- 开发用于分析编译阶段的技术
- 与 AI 编译器工具链的其他工程师密切合作
- 提高编译器在各种神经网络和不同硬件上的可靠性和性能
必备要求
- 在欧洲一流大学攻读计算机科学/电气工程或相关领域的学位
- 具备 C++ 和/或 Python 的知识和实践经验
- 具备扎实的软件工程原理、数据结构、设计模式和算法知识
- 熟悉 Linux、Git 和常用软件开发工具
- 具备解决复杂问题的雄心和好奇心，拥有强烈的责任感，能够主动承担任务，推动解决方案的进展，并拥有协作精神
优先条件
- 有使用 MLIR 或 LLVM 的经验
- 对开源编译器社区做出有意义的贡献
- 具备人工智能算法知识，有使用人工智能加速器或编译到相关硬件的经验
- 神经网络知识
- 具备 CPU、GPU 或 NPU/加速器硬件架构方面的知识
Responsibilities
- Improve our automated benchmarking infrastructure to keep up with emerging state-of-the-art AI models
- Develop tools for finding compiler accuracy
- Develop techniques for analyzing compilation stages
- Work closely with other engineers on our AI compiler toolchain
- Improve the reliability and performance of our compiler across various neural networks and different hardware
Must Have
- Pursuing a degree in Computer Science/Electrical Engineering or a related field at a top European university
- Knowledge and hands-on experience with C++ and/or Python
- Solid knowledge of software engineering principles, data structures, design patterns, and algorithms
- Familiarity with Linux, Git, and common software development tools
- Ambition and curiosity to solve complex problems, strong sense of responsibility, ability to take initiative and drive solutions forward, and a collaborative spirit
Preferred
- Experience with MLIR or LLVM
- Meaningful contributions to the open-source compiler community
- Knowledge of AI algorithms and experience with AI accelerators or compiling to relevant hardware
- Knowledge of neural networks
- Knowledge of CPU, GPU, or NPU/accelerator hardware architectures
公司简介
Roofline 正在构建一个软件开发工具包，用于在边缘端的高性能硬件上运行任何模型。在 RooflineAI，我们助力您实现梦寐以求的边缘人工智能产品。我们的使命很简单：将芯片的强大功能带给创新者，并让他们能够更轻松地在顶尖硬件上使用尖端人工智能模型。