Podcast
From Classical Guitar to Production ML: Nonlinear Career Path Through Semiconductors, Yield Analytics & Community-Driven Learning
Open original DataTalks.Club episode
From Classical Guitar to Production ML: Nonlinear Career Path Through Semiconductors, Yield Analytics & Community-Driven Learning
Original Episode
Use these links for the canonical episode and media sources.
- Open the original DataTalks.Club podcast page
- Watch on YouTube
- Listen on Spotify
- Listen on Apple Podcasts
Episode Overview
How do you move from playing classical guitar to applying machine learning in semiconductor yield analytics? In this episode Dashel Ruiz Perez — a data analyst, ML engineer, and educator — walks us through a nonlinear career path that spans nearly a decade at Microchip Technology and now teaching programming and data skills through ThriveDX. With roles across production, process, yield, and software engineering, Dashel explains how hands-on production experience informs production analytics and ML engineering work.
People
Use these links to connect the episode to guest notes.
Chapter Summary
Use these checkpoints to decide whether to open the source transcript.
- 0:00 - Podcast Introduction & DataTalksClub
- 1:51 - Guest Overview: Multidisciplinary Career Snapshot
- 2:58 - Career Pivot: From Classical Guitarist to Tech in Portland
- 4:49 - Semiconductor Onboarding: Expediter Role and Fab Floor Experience
- 5:49 - Fab Data Exposure: Millisecond Tool Logs and Process Telemetry
- 6:16 - Self-Education: Learning English and Computer Science
- 11:44 - Automation Initiative: Building a Java Tool for CMP Calculations
- 15:23 - Yield Analytics: JMP, Oracle, and Cross-Area Data Access
- 21:02 - ML Introduction: Academic AI Project and Predictive Interest
- 23:29 - Predictive Maintenance: “Wafers at Risk” Model for Yield Improvement
- 25:16 - Explainability Dilemma: Tweaking Models vs. Understanding Results
- 29:33 - Course Selection: Choosing ML Zoomcamp Cohort Experience
- 32:22 - Applied Curriculum: Deliverable ML Beyond Jupyter Notebooks
- 34:34 - Learning Support: Slack Q&A, Cohorts, and Peer Study Groups
- 37:29 - Production Focus: Flask REST API, Docker, and Google Cloud
- 39:52 - Midterm Demo: COVID Comorbidity Model Deployed as an API
- 44:36 - Infrastructure Automation: Terraform and MLOps Takeaways
- 48:24 - Computer Vision Project: Butterfly Image Classification (TensorFlow)
- 51:10 - Kaggle Workflow: EDA, Feature Engineering, and Model Iteration
- 51:53 - Model Portability: ONNX for Framework Interoperability
- 53:23 - Full-Stack ML Skills: Docker, VMs, Databases, and Deployment
- 54:25 - Common Roadblocks: Mac M1 Issues and Wide Categorical Data
- 56:02 - Time Commitment: Homework Strategy and Active Video Learning
- 58:07 - Community Value: Rapid Help, Code Reviews, and Study Groups
- 1:00:31 - Motivation Techniques: Public Learning and Project Accountability
- 1:07:36 - Teaching Ambition: Creating High-Quality Spanish ML Content
- 1:10:28 - Upcoming Offerings: AI-for-Developers, React, and LLM Coding
- 1:12:49 - Closing Remarks: Course Endorsement and Next Steps