Staff Engineer (Fleet Performance)

View full description

Requirements:

• Bachelor's or Master's degree in Computer Science, Mathematics, Statistics, or Computer/Electrical Engineering or equivalent work experience.
• Extensive knowledge of Linux kernel, hypervisors, and open-source operating systems.
• 7+ years of experience with performance measurement tools such as profilers, eBPF, XDP, fio, TPCC, MLPerf, and NCCL.
• 5+ years of experience developing strategies for managing, monitoring, and analyzing infrastructure, applications, and services.
• Strong proficiency in Go, Python, or Ruby.
• Deep understanding of kernel performance aspects, including scheduling, context switching, and hardware acceleration.
• Expertise in distributed systems performance.
• Knowledge of GPU technology and programming for multi-GPU workloads.
• Proven problem-solving ability at scale.
• Strong security mindset with best practices.
• Excellent collaboration and communication skills.
• Leadership experience in skills development and mentorship.
• Professional-level written and spoken English with strong presentation abilities.

Responsibilities:

• Develop and implement comprehensive performance metrics, analysis tools, and reporting systems.
• Lead initiatives to enhance shared infrastructure, balancing performance optimization with security standards.
• Collaborate with hardware engineering teams and vendors to validate GPU fabric performance.
• Engage with the open-source Linux community to advance virtualization technologies.
• Conduct in-depth performance analysis to devise optimization strategies.
• Identify system bottlenecks and drive optimizations across the hypervisor software stack.
• Work cross-functionally to harness new performance capabilities from evolving hardware architectures.
• Enhance test frameworks and pipelines for robust performance validation.
• Investigate and resolve virtual machine downtime and performance issues.
• Participate in on-call rotations to support system reliability.