•Job Summary
We are seeking an engineer to build scalable automation, telemetry and analytics capabilities for AI PC thermal, power, performance and reliability validation. The role converts engineering test methods into reusable Python and PowerShell frameworks that orchestrate workloads, collect sensor data, apply automated checks, detect regressions and generate decision-ready reports. The engineer will also apply statistics and practical machine learning to identify abnormal platform behavior and improve diagnostic efficiency across CPU, GPU, NPU, memory, storage, firmware, drivers and Windows-based systems.
•Key Responsibilities A. Validation Framework Development
•Design and develop modular automated validation frameworks using Python and PowerShell.
•Automate benchmark execution, workload control, sensor-data collection, configuration capture and result packaging.
•Build reusable test suites that support multiple PC models, processor architectures and hardware configurations.
•Implement parameterized test execution, automated pass/fail logic, threshold s and regression detection.
•Integrate test utilities with structured logs, result stores, dashboards and engineering reports.
•Apply software-engineering practices including code review, version control, exception handling and maintainable documentation.
B. Telemetry and Data Engineering
•Collect, normalize and correlate temperature, power, frequency, utilization, fan, workload and benchmark telemetry.
•Design schemas for test metadata, platform configuration, time-series measurements, errors and verdicts.
•Create data-quality checks for missing samples, sensor inconsistencies, time alignment and invalid test conditions.
•Develop repeatable pipelines for comparing builds, firmware versions, drivers and hardware configurations.
•Create visualizations for thermal curves, power profiles, workload performance, stability and cross-platform comparisons.
C. Statistical and AI-Assisted Analysis
•Apply descriptive statistics, regression, anomaly detection and time-series analysis to validation datasets.
•Develop practical models or rules to identify unusual thermal, power and performance behavior.
•Explore predictive indicators for thermal throttling, workload slowdown and system degradation.
•Correlate workload characteristics, utilization, temperature, power and delivered performance.
•Develop AI-assisted diagnostic recommendations while retaining traceable evidence and engineer review.
•Use established libraries and frameworks where appropriate, avoiding unnecessary model complexity.
D. AI Workload and Cross-Platform Automation
•Automate AI inference workload execution and compare latency, throughput, memory usage and energy consumption.
•Support CPU, GPU and NPU execution paths and capture runtime, driver and model configuration details.
•Enable comparative testing across Intel, AMD, NVIDIA and supported ARM-based platforms, including applicable Qualcomm Snapdragon systems.
•Assess workload compatibility across Windows versions, drivers and supported AI runtimes such as ONNX Runtime where applicable.
•Provide reliable, repeatable data packages for platform and product engineering decisions.
E. Engineering Enablement and Reporting
•Work with validation engineers to translate manual procedures into safe, repeatable automated workflows.
•Develop concise reports that explain test scope, data quality, detected regressions and recommended investigation paths.
•Maintain test framework documentation, configuration records, release notes and validation evidence.
•Improve automation coverage, execution efficiency, traceability and regression-detection speed.
•Triage framework failures separately from product failures and provide actionable debug information.
•Required Technical Skills
Programming and automation: Strong Python; PowerShell or Windows command-line scripting; pytest or an equivalent test framework; modular design, error handling and maintainable code.
Data and visualization: pandas, NumPy and Matplotlib; structured logs; time-series data; result normalization; dashboards or automated engineering reports.
Statistics and machine learning: Regression, anomaly detection, telemetry correlation and model validation; familiarity with scikit-learn, PyTorch, ONNX Runtime or equivalent.
PC systems knowledge: Working understanding of CPU, GPU, NPU, memory, storage, thermal and power management, Windows, BIOS/UEFI, firmware and drivers.
Performance tooling: Ability to automate or integrate tools such as HWiNFO or equivalent, Cinebench, OCCT, 3DMark or comparable benchmarks, CrystalDiskMark and Windows Performance Recorder/Analyzer.
Engineering practices: Git-based version control, code review, issue tracking, test traceability, documentation and reproducible execution environments.
•Preferred Qualifications
•Bachelor's or master's degree in Computer Engineering, Electrical Engineering, Computer Science, Data Science or a related discipline.
•Four or more years of experience in test automation, system validation, performance engineering, data engineering or a related field.
•Demonstrated experience developing Python-based automation for hardware, systems or laboratory testing.
•Experience processing hardware telemetry or benchmark datasets and producing automated reports.
•Familiarity with Windows performance diagnostics and hardware or firmware troubleshooting.
•Experience with AI inference workloads, ONNX Runtime, scikit-learn, PyTorch, dashboards or time-series databases is an advantage.
•Key Deliverables
•Reusable automated thermal, power, performance and reliability validation framework.
•Standardized automated test suites for CPU, GPU, NPU, memory and storage workloads.
•Structured telemetry and result data model with data-quality controls.
•Automated regression reports, dashboards and threshold-based s.
•AI-assisted anomaly-detection or thermal-throttling prediction prototype.
•Framework documentation, release notes, test procedures and onboarding guidance.
•Success Metrics
•Percentage of agreed test execution and reporting automated.
•Reduction in manual test effort and regression-detection time.
•Framework reliability, repeatability and successful execution across supported configurations.
•Quality of data capture, traceability and separation of framework failures from product failures.
•Usefulness and validation accuracy of anomaly or regression signals against confirmed engineering results.
•Adoption of reusable automation by validation and laboratory teams.
•Collaboration
The engineer will collaborate with thermal and performance validation, hardware design, BIOS/firmware, operating-system, driver, AI software, quality assurance, laboratory operations, data and product engineering teams.
•Ideal Candidate Profile
The ideal candidate is an automation engineer with enough PC hardware knowledge to build trustworthy validation systems. They should understand how telemetry is produced, recognize invalid test conditions, write maintainable code and communicate analytical results to engineers who make hardware and product decisions.
