> Markdown version of [/jobs/ext/1311056-staff-performance-tuning-engineer-cpu-pmu-virtualization](https://www.wearedevelopers.com/jobs/ext/1311056-staff-performance-tuning-engineer-cpu-pmu-virtualization). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Staff Performance Tuning Engineer (CPU PMU & Virtualization)

- **Company:** NIO
- **Location:** San Jose, CA, United States
- **Experience:** Expert
- **Salary:** $192,100.0 - $249,600.0
- **Contract:** Permanent contract
- **Skills:** ARM Architecture, C++ (Programming Language), Microarchitecture, Linux, Python (Programming Language), Kernel-Based Virtual Machine, Performance Tuning, Quick EMUlator (QEMU), Real-Time Operating Systems, Shell Script, System Software, Virtual Memory, Virtualization Technology, Xen Servers, Backend, Information Technology, Performance Monitor, Front End Software Development
- **Published:** July 17, 2026
- **Apply:** https://www.dice.com/job-detail/0ce49500-aea2-42e0-9b7d-b66e305c75ec

## About the Role

* Bachelor's, Master's, or Ph.D. in Computer Science, Electrical Engineering, or a related field.
 * 8+ years of experience in system performance engineering or related roles.
 * Strong understanding of computer architecture, including:
 + CPU pipelines, execution engines, and memory hierarchy
 + Interrupt architectures (e.g., GICv3/GICv4, APIC concepts)
 + MMU, virtual memory, and page table structures
 * Deep expertise with Linux performance tooling:
 + perf
 + eBPF / BCC / bpftrace
 + ftrace / trace-cmd
 * Proficiency in C/C++, Python, and shell scripting for performance tooling and automation.

Preferred Qualifications

 * Hands-on experience with ARM PMUv3 on Cortex-A55/A76/A78 or Neoverse platforms.
 * Experience with one or more virtualization stacks:
 + KVM/QEMU
 + Xen
 + seL4 or other RTOS/hypervisor environments

## Description

Performance Analysis and Optimization

 * Identify and analyze performance bottlenecks across CPU, memory hierarchy, cache, interconnect, and interrupt subsystems.
 * Leverage hardware PMU counters to measure and interpret cycles, instructions, cache misses, branch mispredictions, TLB misses, and stall cycles.
 * Compute and analyze performance metrics such as IPC, CPI, MPKI, memory bandwidth utilization, and stall breakdowns.
 * Optimize system software, applications, and drivers for throughput, latency, and performance determinism.

Virtualization Performance Tuning

 * Profile and reduce hypervisor overhead, including VM exits, interrupt injection, and stage-2 MMU translation costs.
 * Optimize vCPU placement strategies, huge page usage, and IRQ affinity for performance-sensitive workloads.
 * Analyze and tune virtio and IOMMU performance paths.
 * Investigate cross-core and cross-cluster latency issues, including IPI overhead and interrupt routing on ARM-based systems.

CPU PMU and Microarchitectural Analysis

 * Configure and interpret ARM PMUv3 and related vendor-specific performance monitoring extensions.
 * Apply Top-Down Microarchitecture Analysis (TMA) to identify frontend/backend bottlenecks.
 * Correlate PMU-derived metrics with kernel traces, source code paths, and system behavior.
 * Design and implement custom event sets tailored to workload-specific performance characterization.


## Related Videos

- [Developing the Backend with Stefan Lingler, CTO at Shpock](https://www.wearedevelopers.com/videos/100360-developing-the-backend-with-stefan-lingler-cto-at-shpock)
- [Docker network without Docker](https://www.wearedevelopers.com/videos/1418-docker-network-without-docker)
- [Unleashing the Full Potential of the Arm Architecture – Write Once, Deploy Anywhere](https://www.wearedevelopers.com/videos/940-unleashing-the-full-potential-of-the-arm-architecture-write-once-deploy-anywhere)
- [Docker exec without Docker](https://www.wearedevelopers.com/videos/1094-docker-exec-without-docker)
- [Scoring 2000 Products per Request: Performance Pitfalls in Golang](https://www.wearedevelopers.com/videos/2073-scoring-2000-products-per-request-performance-pitfalls-in-golang)
- [Nest.js - TypeScript in the backend can also be clean](https://www.wearedevelopers.com/videos/1033-nest-js-typescript-in-the-backend-can-also-be-clean)

## Related Articles

- [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers)
- [Highest Paying Tech Companies for Developers](https://www.wearedevelopers.com/magazine/220-highest-paying-tech-companies-for-developers)
- [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline)
- [7 Cloud Computing Trends Coming in 2025 for Developers](https://www.wearedevelopers.com/magazine/412-7-cloud-computing-trends-coming-in-2025-for-developers)
- [Is Software Engineering Over-Saturated?](https://www.wearedevelopers.com/magazine/418-is-software-engineering-over-saturated)
- [6 Emerging Technologies We’ll Learn About in 2025](https://www.wearedevelopers.com/magazine/381-6-emerging-technologies-we-ll-learn-about-in-2025)