We are seeking a Staff Engineer – Performance with strong expertise in data path and I/O performance for large-scale distributed file systems. This role focuses on analyzing, optimizing, and improving performance across the storage stack, from low-level code paths to system-wide behavior at scale.
You will work closely with architects and cross-functional teams to investigate complex performance issues, implement optimizations, and ensure high throughput and low latency in distributed systems. This role emphasizes hands-on technical contributions, performance tuning, and data-driven decision-making to improve overall system efficiency and reliability.
Key Responsibilities:
Contribute to the performance design of data path and I/O components in distributed file systems
Perform performance analysis, troubleshooting, and optimization of large-scale, high-performance file systems
Implement performance-aware improvements across CPU, memory, storage, and network layers
Optimize performance-critical file system code, primarily in C++
Apply best practices for performance measurement, profiling, benchmarking, and regression detection
Investigate and resolve complex system-level performance issues
Collaborate with architects and senior engineers to incorporate performance considerations into system design
Work with cross-functional teams to validate and meet performance goals across the stack
Participate in design reviews with a focus on performance implications
Share knowledge and support peers in adopting effective performance engineering practices
Requirements:
Accountable and highly motivated with solid people skills
10+ years’ experience system software development and complex problem resolution.
Deep understanding of distributed file systems and scale-out storage architectures
Expert-level knowledge of data path and I/O path design and optimization
Strong proficiency in C++ with extensive experience in performance-critical code
Proven expertise in performance measurement techniques, including profiling, tracing, benchmarking, and custom tooling
Strong foundation in distributed systems principles, including scalability, concurrency, and fault tolerance
Demonstrated experience optimizing file system or storage system code for performance at scale
Experience with high-performance, high-scale-out file systems in production environments
What Success Looks Like
Consistently delivers measurable improvements in throughput, latency, and scalability
Identifies and mitigates performance bottlenecks early in the development lifecycle
Produces reliable performance analysis that informs design and implementation decisions
Contributes to stable, repeatable performance testing and regression detection practices
Effectively collaborates with team members to meet performance goals across components
Builds and applies strong performance engineering expertise to improve code and system quality