Senior Ethernet Performance Engineer (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Senior Ethernet Performance Engineer (AI/HPC): Leading performance validation and characterization of next-generation Ethernet-based networking silicon products with an accent on RoCEv2, RDMA, and high-performance compute environments. Focus on benchmarking fabrics, root-causing performance anomalies, and optimizing system throughput and latency for AI and HPC workloads.
Location: Remote (Must be residing within the United States). Occasional travel to Wayne, PA is required.
Company
delivers high-performance scale-out networking solutions for AI and HPC datacenters.
What you will do
- Build, configure, and benchmark Ethernet fabrics with RoCEv2 for head-to-head evaluations against other network architectures.
- Develop and execute performance test plans for internal labs and real-world data center deployment scenarios.
- Analyze key performance metrics including throughput, latency, congestion, and power efficiency.
- Collaborate with customers and field teams to debug and optimize performance issues in production environments.
- Create diagnostic tools and scripts to collect, analyze, and visualize performance data.
- Provide actionable feedback to silicon and system design teams to resolve performance anomalies.
Requirements
- 7+ years of experience in post-silicon validation, performance engineering, or silicon debug for networking/HPC products.
- Strong understanding of networking protocols (Ethernet, PCIe) and congestion control (PFC, ECN, DCQCN).
- Proficiency in Python and Shell scripting for automation.
- Experience with data center performance requirements and benchmarks.
- Strong cross-functional communication skills and comfort working directly with customers.
- Must be residing within the United States.
Nice to have
- Deep understanding of DPDK, RDMA, or similar high-performance I/O frameworks.
- Background in silicon performance modeling or firmware/hardware co-design.
- Experience running HPC (MPI) and AI (NCCL/RCCL) benchmarks.
- Expertise in investigating PFC deadlocks and tail latency using kernel tools and fabric telemetry.
Culture & Benefits
- Competitive compensation package including equity, cash, and performance incentives.
- Comprehensive health, dental, and vision insurance, plus disability and life insurance.
- 401(k) plan with company match.
- Flexible work environment with Open Time Off (OTO), sick time, and paid holidays.
- Opportunity to collaborate with influential names in the semiconductor industry.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →