Senior Deep Learning Frameworks CUDA Software Engineer

免费注册后解锁"你的匹配分 vs 高分画像"与个人技能缺口。

NVIDIA is leading the way in groundbreaking developments in Artificial Intelligence, High Performance Computing and Visualization. The GPU, our invention, serves as the visual cortex of modern computers and is at the heart of our products and services. Our work opens up new universes to explore, enables amazing creativity and discovery, and powers what were once science fiction inventions from artificial intelligence to autonomous cars. We are looking for a motivated Deep Learning engineer to bring advanced CUDA features and Distributed Runtime technologies into AI stacks, including PyTorch, TRT-LLM, vLLM, SGLang, JAX, etc. You will be working with the team that created core CUDA features and runtimes for scaling Deep Learning and HPC applications. Your customers will have diverse multi-GPU demands, ranging from training on scales up to 100K GPUs to inference down at microsecond latency. CUDA features improve both productivity and performance of AI applications. Your work in AI toolkits will accelerate enabling those for the community. This is an outstanding opportunity for someone with an AI background to advance the state of the art in this space. Are you ready to contribute to the development of innovative technologies and help realize NVIDIA 's vision? What you will be doing: Integrate new CUDA features and Runtime abstractions in AI frameworks: from PoC to performance analysis to production Perform deep analysis of AI workloads and frameworks to identify requirements and opportunities to innovate in the lower layers of the stack. Collaborate hands-on with teams working on the latest AI models. Own and drive improvements in the AI Compiler-Runtime interface to build speed-of-light multi-GPU multi-node solutions. Design fault-tolerant and elastic solutions for large-scale or dynamic AI workloads. Influence the roadmap of core CUDA to facilitate building next-gen DL frameworks. Collaborate with a very dynamic team across multiple time zones. Collaborate closely with AI researchers, HW and SW architects, kernel and compiler authors and CUDA driver experts to co-design systems and frameworks that enhance performance and programmability. Develop exploratory tools and runtime systems to profile and accelerate new paradigms in deep learning. Write clean, effective, and maintainable code, ensuring exploratory prototypes can smoothly transition into open-source releases, upstream framework integrations, internal tools, or closed-source commercial products. What we need to see: BS, MS, or PhD degree in Computer Science, Computer Engineering, Electrical Engineering, or related field (or equivalent experience). 8+ years of relevant industry experience or equivalent academic experience after completed degree. Development experience with Deep Learning Frameworks such PyTorch, JAX, and Inference Engines such as TRT-LLM, vLLM, SGLang Rapid prototyping and development with Python, C++, CUDA or related DSLs Solid grasp of AI models, parallelisms, and/or compiler technologies (e.g. torch.compile) Experience conducting performance benchmarking on AI clusters. Familiarity with at least one performance profiler toolchain (PyTorch profiler, NVIDIA Nsight Systems) Understanding of HPC/AI communication concepts Good understanding of computer system architecture, HW-SW interactions and operating systems principles (aka systems software fundamentals) Adaptability and passion to learn new frameworks and tools Flexibility to work and communicate effectively across different teams and timezones Ways to stand out from the crowd: Deep expertise in the performance internals and execution graphs of major deep learning autograd, training and inference frameworks (e.g., PyTorch, JAX, TensorRT, vLLM, sgLang, Nemo, Megatron, MaxText, etc.). Hands-on experience with CUDA, specific communication libraries (e.g., NCCL, MPI, UCX) and distributed machine learning techniques (e.g., pipeline parallelism, tensor parallelism). Expertise in one or more of these areas: T

NVIDIA 在人工智能、高性能计算和可视化领域的突破性发展中处于领先地位。GPU，我们的发明，作为现代计算机的视觉皮层，是我们产品和服务的核心。我们的工作开辟了新的宇宙供探索，激发了惊人的创造力和发现，并驱动了曾经是科幻小说中的发明，从人工智能到自动驾驶汽车。我们正在寻找一位有动力的深度学习工程师，将先进的 CUDA 功能和分布式运行时技术引入 AI 栈，包括 PyTorch、TRT-LLM、vLLM、SGLang、JAX 等。您将与创建核心 CUDA 功能和运行时的团队合作，这些功能和运行时用于扩展深度学习和 HPC 应用。您的客户将有多样化的多 GPU 需求，从高达 100K GPU 的训练到微秒级延迟的推理。CUDA 功能提高了 AI 应用的生产力和性能。您在 AI 工具包中的工作将加速为社区启用这些功能。对于有 AI 背景的人来说，这是一个推动该领域最先进技术的绝佳机会。您准备好为创新技术的发展做出贡献，并帮助实现 NVIDIA 的愿景了吗？您将做什么：在 AI 框架中集成新的 CUDA 功能和运行时抽象：从 PoC 到性能分析再到生产。对 AI 工作负载和框架进行深入分析，以识别在栈的较低层进行创新的需求和机会。与从事最新 AI 模型的团队进行动手协作。拥有并推动 AI 编译器-运行时接口的改进，以构建光速多 GPU 多节点解决方案。为大规模或动态 AI 工作负载设计容错和弹性解决方案。影响核心 CUDA 的路线图，以促进构建下一代深度学习框架。与跨多个时区的非常动态的团队合作。与 AI 研究人员、硬件和软件架构师、内核和编译器作者以及 CUDA 驱动专家密切合作，共同设计系统和框架，以增强性能和可编程性。开发探索性工具和运行时系统，以分析和加速深度学习中的新范式。编写干净、有效和可维护的代码，确保探索性原型能够顺利过渡到开源发布、上游框架集成、内部工具或闭源商业产品。我们需要看到：计算机科学、计算机工程、电气工程或相关领域的学士、硕士或博士学位（或同等经验）。8 年以上相关行业经验或完成学位后的同等学术经验。具有深度学习框架（如 PyTorch、JAX）和推理引擎（如 TRT-LLM、vLLM、SGLang）的开发经验。使用 Python、C++、CUDA 或相关 DSL 进行快速原型设计和开发。对 AI 模型、并行性和/或编译器技术（例如 torch.compile）有扎实的理解。具有在 AI 集群上进行性能基准测试的经验。熟悉至少一种性能分析器工具链（PyTorch profiler、NVIDIA Nsight Systems）。了解 HPC/AI 通信概念。对计算机系统架构、硬件-软件交互和操作系统原理（即系统软件基础）有良好的理解。适应性和学习新框架和工具的热情。灵活地在不同团队和时区工作和有效沟通。脱颖而出的方式：在主要深度学习自动微分、训练和推理框架（例如 PyTorch、JAX、TensorRT、vLLM、sgLang、Nemo、Megatron、MaxText 等）的性能内部结构和执行图方面具有深厚专业知识。具有 CUDA、特定通信库（例如 NCCL、MPI、UCX）和分布式机器学习技术（例如流水线并行、张量并行）的实践经验。在以下一个或多个领域的专业知识：T

⚑ 岗位信息收录自公开招聘页（Himalayas），以雇主官网为准