Job Responsibilities:
-Performance Leadership: Drive the assessment, benchmarking, profiling, debugging and integration of new server systems and architectures that support diverse application stack
-Analyze application performance across various hardware components (CPUs, GPUs, storage and memory subsystems) in both virtual machines and bare metal in order to optimize for cost, performance and utilization
-Cross-functional Collaboration: Act as a central figure in aligning teams from different technical backgrounds The cloud shape benchmarking, storage platform, and service teams to drive comprehensive solutions to performance challenges
-Advanced Troubleshooting and Optimization: Leverage your deep knowledge of the most effective tools and processes to drive deep and effective performance debugging
-Propose and implement optimizations that enhance both hardware utilization and software performance
-Technical Recommendations and Implementations: Evaluate and recommend new tools and technologies that can improve performance benchmarking velocity and effectiveness
-Develop and adjust benchmarking suites and methodologies for various software technologies such as Java, Golang, open-source database, Apache Kafka, and machine learning applications
-Work with the benchmarking team to incorporate both stand-alone, and production resource sharing benchmarks into internal benchmark framework
-Knowledge Sharing and Best Practices: Serve as a knowledge leader, sharing insights and best practices for system and workload profiling, debugging and telemetry collection
Required Skills and Qualifications:
-Proven Experience: 8 years in performance engineering, including direct hands-on experience with server systems and an understanding of CPU microarchitecture, storage, memory, and GPU technologies
-Technical Expertise: Proficiency in performance benchmarking and optimization, with solid experience using tools such as flamegraph, Linux perf, eBPF, and synthetic benchmarking suites like specCPU2017, specJBB, MLperf
-Additional expertise in application specific benchmarks for databases, event streaming, Golang, etc would be beneficial
-Software and Systems Knowledge: Strong background in software engineering, with at least 5 years of experience
-Deep understanding of Linux kernel, compilers, middleware technologies (Java, Golang, TensorFlow, PyTorch), and container environments (Kubernetes, Docker)
-Communication and Collaboration: Excellent communication skills with the ability to lead and integrate efforts across multiple teams
-Autonomy: Capable of working independently with a high degree of autonomy to make informed decisions and drive necessary changes