Senior Product Reliability Engineering

AMD AMD · Semiconductors · Austin, TX · Engineering

Senior Product Quality Engineer at AMD focusing on improving quality and reliability of Server CPUs and Instinct accelerators by developing and deploying ML/AI solutions for manufacturing and test data analysis. The role involves identifying use cases, building production-ready analytics, performing root-cause analysis, and driving adaptive test strategies.

What you'd actually do

  1. Partner with Product Engineering, Test Engineering, Yield Engineering, Quality, and Operations to identify, define, and prioritize analytics and machine‑learning use cases that materially improve yield, quality, and cost.
  2. Develop and deploy ML/AI solutions for parametric outlier screening, drift detection, and excursion/anomaly detection across wafer, lot, site, and package dimensions.
  3. Perform in‑depth root‑cause analysis of yield loss and DPPM drivers by correlating test, fab, assembly, and design variables; distinguish systemic issues from statistical noise.
  4. Build, productionize, and maintain yield and quality analytics within AMD’s AVA analytics platform, moving models from experimentation to scalable deployment.
  5. Drive adaptive test, screening, and binning strategies using data‑driven insights to optimize product quality and manufacturing efficiency.

Skills

Required

  • Python
  • SQL
  • statistics
  • machine learning
  • hypothesis testing
  • DOE/RSM
  • regression
  • classification
  • outlier detection
  • time-series analysis
  • anomaly detection
  • semiconductor manufacturing
  • test flows
  • wafer sort
  • final test
  • binning strategies
  • DPPM analysis
  • reliability screens
  • excursion management

Nice to have

  • server-class CPUs
  • accelerator/GPU products

What the JD emphasized

  • production-ready analytics
  • machine-learning solutions
  • production environments
  • deploy analytics or ML solutions into production environments

Other signals

  • Develop and deploy ML/AI solutions
  • productionize and maintain yield and quality analytics
  • moving models from experimentation to scalable deployment