About the role We are building out a team dedicated to optimizing the performance of Uber's critical workloads. Our mission is to ensure that workloads running across Uber's infrastructure perform at peak efficiency, minimizing latency, maximizing throughput and ensuring optimal resource usage. A key focus of the team is to develop systems for continuous workload performance analysis, regression detection and optimization, enabling performance improvements at scale.
The role emphasizes designing and building systems that help optimize workload performance across a diverse infrastructure, including bare metal hosts, VMs, on-prem data centers, and multiple cloud vendors. You will work closely with other teams to identify performance bottlenecks, mitigate inefficiencies, and address challenges such as noisy neighbor problems in colocated environments. Additionally, you will be responsible for building systems that help quickly troubleshoot performance issues in production, ensuring Uber's workloads remain highly performant and stable.
As part of this growing team, you will have the opportunity to shape the future of performance-driven workload optimization at Uber, contributing to the development of systems and tools to drive these improvements.
Basic Qualifications
- 2+ years of experience
- BS, MS, or Ph D in computer science, or similar technical fields with hands-on performance engineering experience
- Strong experience or interest in performance analysis, tuning, benchmarking and troubleshooting performance issues in production on Linux systems
- Proficiency in multiple programming languages (e.g., C/C++, Go)
- Proven ability to collaborate across teams to build systems at scale
- Excellent communication and analytical skills with a focus on performance analysis and reporting, postmortems, and technical documentation
Preferred Qualifications
- Strong understanding of Linux kernel internals with a focus on workload performance
- Expertise in hardware and software performance tuning at scale
- Expertise in profiling tools (e.g., perf, e BPF) and debugging complex performance issues
- Experience with containerization and orchestration platforms (Kubernetes, Docker)
- Familiarity with cloud infrastructure (AWS, GCP), particularly in tuning for large-scale workload performance
- Comfortable working with high-performance on-prem and cloud-based infrastructure
- Experience contributing to the development of systems for performance analysis and optimization