Splunk Senior Staff Software Engineer - Performance Optimization & Innovation (PerfOpt)

Cisco is a technology company focused on data and infrastructure solutions to connect and protect organizations in the AI era and beyond. The role is within the Performance Optimization and Innovation (PerfOpt) team at Splunk, which improves customer experience through deep performance work on petabyte-scale data in a large distributed architecture.

• Expert-level proficiency in production C++ including memory management, move semantics, and cache-friendly data structures.
• Deep performance engineering experience with CPU/memory profiling, flame graph analysis (perf, eBPF, VTune), lock contention resolution, and latency optimization in distributed architectures.
• Experience with benchmarking, performance modeling, and system design.
• Familiarity with Docker and Kubernetes performance characterization.
• Strong Python skills for tooling, benchmarking, and performance data analysis.
• Knowledge of Linux performance internals including scheduler, memory subsystem, page cache, filesystems, block I/O, and network stack.
• Experience with Git and CI systems such as GitLab CI.
• Proven leadership skills with ability to inform leadership decisions, communicate complex problems clearly, and mentor engineers.

Preferred Qualifications:

• Experience with petabyte-scale data flows, object storage (S3), caching, and I/O workload management.
• Familiarity with Splunk internals or comparable large-scale data platforms.
• Background in storage/query engine or distributed search optimization.
• Hardware-level optimization techniques including SIMD, NUMA, cache/TLB behavior, PGO/LTO, compiler optimization.
• Experience with systems languages like Go or Rust alongside C++.
• Knowledge of AWS, Azure, or GCP storage, networking, and compute performance.
• Experience with Terraform, Puppet, or Ansible for reproducible performance test environments.

• Serve as the performance authority for critical issues, roadmap planning, architecture reviews, and customer conversations.
• Lead a performance domain end to end including hypothesis, instrumentation, design, and measuring customer-visible gains in production.
• Architect and re-architect subsystems for scalability and performance in distributed systems.
• Define and maintain performance methodology including profiling, flame graph analysis, lock contention resolution, benchmarking, and regression gating.
• Design new telemetry sources and implement observability using eBPF and continuous profiling.
• Enable leadership decisions by quantifying trade-offs, risks, and recommendations.
• Build reusable AI agentic workflows and tooling to accelerate performance analysis.
• Lead and mentor senior and staff engineers.