NVIDIA
- 19/12/2023
- קרית אתא
We are seeking a talented and experienced performance analysis engineer to join our team. As a Performance Engineer Engineer focused on AI applications, you will play a crucial role in optimizing the performance of our Spectrum-X platform, the first networking platform for AI. Powered by the tight coupling of the NVIDIA Spectrum™-4 Ethernet switch and the NVIDIA® BlueField®-3 data processing unit (DPU), Spectrum-X delivers the highest performance for AI, machine learning, and natural language processing, as well as diverse industry applications.What You Will Be Doing
- Network Performance Analysis: Conduct in-depth analysis of network performance, including latency, throughput, and packet loss, using various monitoring tools and techniques. Identify bottlenecks and areas for improvement in the network infrastructure.
- Performance Optimization: Develop strategies and implement solutions to optimize the performance of the network infrastructure which includes Switch, DPU and SW. Collaborate with cross-functional teams, including architects, AI engineers and system administrators, to implement and test performance-enhancing configurations.
- Network Monitoring and Testing: Deploy and maintain network monitoring tools to continuously monitor network performance and proactively identify potential issues. Develop and execute performance testing methodologies to assess the impact of Product changes on AI application performance.
- Troubleshooting and Issue Resolution: Investigate and resolve networking-related issues that impact AI application performance. Stay Abreast of Emerging Technologies: Keep up-to-date with the latest benchmarks, networking technologies, industry trends, and best practices related to AI application performance. Evaluate and recommend new tools, methodologies, and technologies that can enhance the efficiency and effectiveness of network performance optimization.
- Bachelor's or Master's degree in Computer Science, Electrical Engineering, or a related field.
- Solid experience in performance engineering, with a focus on AI applications.
- 8+ years of experience
- Proficiency in network protocols, including TCP/IP, UDP, HTTP, and RDMA.
- Experience with software design and development
- Experience with network performance testing tools
- Strong analytical and problem-solving skills to identify and resolve SW and HW performance issues.
- Excellent communication skills, with the ability to collaborate effectively with cross-functional teams and present complex concepts to both technical and non-technical stakeholders.
- Proactive and self-motivated, with the ability to work independently and prioritize tasks effectively.
- Previous experience as a performance engineer
- Strong Python and scripting skills
- Experience with debugging HW like DPUs GPUs and CPUs
רוצה לראות עוד משרות מתאימות? Jobify מנתחת את הניסיון התעסוקתי שלך ומציגה לך משרות עדכניות - בחינם!