Lead Software Engineer - 30962_C
Job Description
Contract opportunities in Phoenix, AZ (hybrid) with BEPC Inc for a Lead Software Engineer supporting advanced SoC performance analysis and optimization. This role focuses on turning processor performance signals into actionable monitoring, diagnostics, and automated characterization for modern Intel platforms.
What you’ll work on
You will design and build automated tools and processes to monitor SoC performance and isolate bottlenecks. Work will span cache, memory bandwidth, and on-die communication fabrics, including LLC occupancy, cache misses, inter-core interference, and contention-driven latency.
- Design, develop, and implement automated SoC performance monitoring tools and workflows.
- Analyze utilization, throughput, latency, and contention across L2/L3 caches, LLC, memory controllers, and on-die fabrics.
- Build performance-monitoring infrastructure using Intel Performance Monitoring Units (PMUs), uncore counters, and diagnostic tooling.
- Monitor LLC occupancy, cache misses, memory bandwidth utilization, and inter-core interference patterns.
- Characterize worst-case latency caused by cache and fabric contention.
- Establish bandwidth allocation limits, QoS parameters, channel priorities, and arbitration policies.
- Evaluate Cache Allocation Technology (CAT), Memory Bandwidth Allocation (MBA), and Intel Resource Director Technology (RDT).
- Analyze performance across Intel Tiger Lake, Ice Lake, Alder Lake, and related architectures.
- Develop automated performance tests, characterization reports, and diagnostic tools.
- Collaborate with engineering teams to identify performance bottlenecks and implement improvements.
- Lead technical investigations and provide guidance for complex performance challenges.
Required qualifications
- 8+ years of experience in SoC performance analysis, processor architecture, or related performance engineering.
- Experience building tooling and processes for hardware performance monitoring.
- Strong understanding of L2/L3 cache behavior, LLC contention, cache occupancy, and memory-controller bandwidth utilization.
- Experience monitoring traffic, throughput, and contention across NoC or on-die communication fabrics.
- Ability to characterize and establish bandwidth allocation limits, QoS values, and channel priorities.
- Experience with Intel Tiger Lake, Ice Lake, or Alder Lake processors.
- Hands-on experience with Intel PMU, uncore performance counters, or comparable monitoring technologies.
- Strong software development, automation, debugging, and analytical skills.
- Bachelor’s degree in Computer Engineering, Electrical Engineering, Computer Science, or a related technical field.
Beneficial experience
- AC20-193 certification experience (high priority).
- Intel Resource Director Technology (RDT)
- Cache Allocation Technology (CAT) and Memory Bandwidth Allocation (MBA)
- Intel Performance Counter Monitor (Intel PCM)
- Cache way partitioning, cache coloring, and bandwidth throttling
- Latency jitter characterization and worst-case execution-time analysis
- NoC performance analysis, fabric utilization, and traffic shaping
- Performance counter correlation and microarchitectural analysis
- Automated performance-monitoring infrastructure for Intel Xeon or Tiger Lake platforms
- QoS enforcement and workload isolation for mixed-criticality systems
- Backgrounds in Intel CPU architecture, platform enablement, hyperscaler performance engineering, Xeon QoS/RDT, networking ASIC/NoC engineering, or automotive multicore timing analysis are encouraged to apply.
Compensation and benefits
Pay: $135.00 - $140.00 per hour. Expected hours: 40.0 per week.
- Dental insurance
- Health insurance
- Life insurance
- Vision insurance
Technologies you may use
- Intel Performance Monitoring Units (PMUs)
- Uncore counters
- Cache Allocation Technology (CAT)
- Memory Bandwidth Allocation (MBA)
- Intel Resource Director Technology (RDT)
- Intel Performance Counter Monitor (Intel PCM)
- Intel Tiger Lake, Ice Lake, Alder Lake
- Intel Xeon
- NoC