Machine Learning Process Engineer

The Process Engineer is responsible for driving process optimization, operational excellence, and continuous improvement initiatives using Lean Six Sigma (LSS) methodologies. This role focuses on improving quality, cost, yield, cycle time, and productivity through structured problem solving, data analysis, and cross‑functional collaboration in a manufacturing environment

Key Responsibilities

• Yield & Defect Analysis: Develop and maintain ML models to identify root causes of package failures (e.g., wire sweep, voiding, or delamination) using sensor and metrology data.
• CV for Automated Inspection: Enhance and deploy Computer Vision (CNN-based) models for Automated Optical Inspection (AOI) to reduce "False Calls" and "Escapes" on the production line.
• Production Deployment: Transition models from local environments (Jupyter/Python) into the factory’s execution system using Docker and REST APIs.
• Process Optimization: Use regression and reinforcement learning to suggest optimal machine parameters (e.g., bond force, temperature profiles) for new product introductions (NPI).
• Data Engineering: Build and manage data pipelines that ingest high-frequency sensor data from packaging equipment (e.g., Die Attach, Wire Bonders) via SECS/GEM or MQTT protocols.A/B Testing & Monitoring: Design experiments to validate model performance on the shop floor and monitor for "model drift" as machine parts wear down over time.
  
  Required Technical Skills
• Core ML: 2+ years of experience with Python (Scikit-Learn, XGBoost, Pandas) and Deep Learning frameworks (PyTorch or TensorFlow).
• Statistical Foundation: Strong grasp of Statistical Process Control (SPC), DOE (Design of Experiments), and Hypothesis Testing.
• Software Engineering: Proficiency with Git, SQL, and Docker. Experience with CI/CD pipelines is a major plus.
• Domain Tools: Familiarity with semiconductor data formats (STDF, ATDF) and visualization tools like Tableau, PowerBI