Software Development Engineer - Data

In this position, the candidate will be working for the Hardware Validation Engineering (HVE) team on post-Silicon hardware system validation of next generation Mac systems. Our Engineering Team is responsible for architecting methods to test new system hardware with the macOS environment to catch issues early in the hardware life cycle. You will be a key technical and logistical contributor and will utilize your in-depth data analytic skills to help provide insight into Hardware behaviors related to Silicon and System performance, power, temperature and fault / error issues.

Description

As a Data Scientist / Analyst within the Hardware team your job responsibilities will include:

Analyze large-scale hardware telemetry including power rails, thermal sensors, Power Silicon and SoC counters and performance logs, and stress-test measurements etc..

Apply statistical modeling and ML techniques to identify anomalies, drift, hardware degradation patterns, and emerging failure signatures.

Develop feature extraction pipelines tailored to silicon behavior-examples: rate-of-change of thermal zones, correlation of voltage droops with workload transitions, PMU-based bottleneck signatures.

Build predictive models that estimate performance/power deviations, reliability risks, or stress-induced failures.

Create clear, high-signal visualizations (e.g., multi-axis time-series overlays, workload-power envelopes, thermal gradients, event timelines) to support hardware debug and performance analysis.

Automate root-cause discovery workflows using statistical correlations, temporal pattern detection, clustering of abnormal runs, and hardware-aware signal decomposition.

Work closely with silicon design, system validation, and performance engineering teams to turn data insights into actionable design or validation recommendations.

Continuously refine modeling and feature engineering methods as new hardware blocks, sensors, counters, and test modes become available.

Data Extraction, Parsing and Storage own the pipeline for extraction and storage into Databases and the structure.

Preferred Qualifications

Experience with dashboard platforms (Grafana, InfluxDB, Plotly Dash, Tableau).

Familiarity with test automation data, debug logs, or hardware lab measurement tools.

Experience in product validation, reliability, performance characterization, or silicon bring-up.

Minimum Qualifications

Bachelor's degree in Computer Engineering, or Computer Science, with 8+ years of experience working with Data Analysis.

Data Science / Statistical Expertise: Strong foundation in Multivariate statistical analysis, Hypothesis testing and experimental design, Time-series modeling (ARIMA, LSTM/GRU ), Anomaly detection (Isolation Forest, HDBSCAN, PCA/ICA, etc). Ability to handle asynchronous, high-frequency hardware telemetry and remove jitter, outliers, and measurement noise.

Programming & Tools: Expert Python skills (Pandas, NumPy, SciPy, Scikit-learn, Matplotlib, Plotly). Ability to write clean, reproducible analytical scripts for large datasets. Strong SQL and experience working with instrumentation data, structured log stores, or validation data warehouses.

Visualization Skills: Ability to produce high-quality, engineering-oriented data visualizations that reveal trends, anomalies, and causal relationships. Must be comfortable creating custom plots and interactive exploratory visualizations using Python and other analytical tools.