logo of nvidia

英伟达Compute Architecture Software Engineer

社招全职地点:上海状态:招聘

任职要求


• 5+ working years' experience in software engineering, particularly in GPU programming and LLM inference.
• Strong proficiency in programming languages such as Python, C++, and CUDA.
• A solid understanding of deep learning frameworks and techniques.
• Outstanding problem-solving skills and the ability to work collaboratively in a team setting.
• Ambitious approach with a proven track record of taking initiative and delivering results.
• BS or above degree in Computer Science, Engineering, or a related field, or equivalent experience.
Widely considered to be one of the technology world’s most desirable emp…
登录查看完整任职要求
微信扫码,1秒登录

工作职责


• You will develop and optimize software solutions to accelerate LLM inference using GPU technology.
• Collaborate closely with a world-class team of engineers to implement and refine GPU-based algorithms.
• Analyze and determine the most effective methods to improve performance, ensuring seamless execution across diverse computing environments.
• Engage in both individual and team projects, contributing to NVIDIA's mission of leading the AI revolution.
• Work in an empowering and inclusive environment to successfully implement groundbreaking AI solutions.
包括英文材料
大模型+
Python+
还有更多 •••
相关职位

logo of nvidia
社招

N/A

更新于 2025-09-17上海
logo of nvidia
实习

We are now looking for a software engineer intern. The NVIDIA Developer Tools team is seeking a software engineer intern to join our effort to advance the state of graphics and compute performance analysis and tuning. You will help developers of groundbreaking products in Automotive, VR, Gaming, Deep Learning and High Performance Computing to analyze and improve the performance of their products. You will have the opportunity to learn the pipeline and driver stack of the world's most sophisticated GPUs, work with a group of talented engineers from all over the world, and apply your software development skills to improve our products. What you’ll be doing: • Develop algorithms to exercise various parts of the GPU pipeline to verify our performance metrics. • Deeply dive into NVIDIA GPU architecture and software stack, develop new feature for NVIDIA GPU performance profiling tools. • Write unit and integration tests to verify the functionality, performance, stability, resource usage of our products.

更新于 2025-11-03上海
logo of amd
社招 Enginee

THE ROLE: The mission of the Principal Technical Lead is to orchestrate and elevate the quality, consistency, and competitiveness of AMD's GPU software ecosystem on Linux. This leader will bridge strategic objectives with technical execution across the ROCm stack and Linux driver portfolios (both packaged and inbox), ensuring a seamless, powerful, and reliable experience for developers, researchers, and enterprises choosing AMD for their accelerated computing needs.   KEY RESPONSIBILITIES: Strategic Technical Leadership & SOW Definition Act as the central technical nexus between Product Management, Software Architecture, and engineering teams (kernel, ROCm, QA, support). Translate high-level product goals and market requirements into detailed, actionable, and prioritized Technical Statements of Work (SOWs) for RSL AI validation team ensure validation plans are coherent, dependencies are managed, and resources are aligned to deliver on strategic commitments for both Radeon and Ryzen AI solutions. Quality, Test & Process Optimization: Own the definition and evolution of the product quality bar for AMD's Linux GPU software. · Champion and drive the implementation of a robust, scalable, and automated CI/CD and test infrastructure across Native Linux, WSL, and various hardware platforms. Establish key performance indicators (KPIs) for software quality, release velocity, and regression rates. Use data to drive continuous improvement in development and testing efficiency Unified User Experience & Competitive Analysis: Define and monitor a holistic user experience (UX) scorecard encompassing installation, performance predictability, documentation, and debugging. Institute a formal, ongoing competitive analysis framework to benchmark the AMD software stack (ROCm + Drivers) against key competitors across performance, feature parity, stability, and usability. Serve as the ultimate internal advocate for the end-user, ensuring customer and community feedback is systematically integrated into the development lifecycle. Linux Ecosystem & Driver Consistency: Provide technical guidance and oversight to ensure flawless synchronization between the AMD packaged driver and the upstream Linux kernel (inbox) driver. Strengthen AMD's partnership with the Linux kernel community and major distributions (e.g., Canonical, Red Hat, SUSE). Drives a consistent and high-quality user experience regardless of the driver delivery channel (OS vendor vs. AMD.com).

更新于 2025-09-24上海