Senior ML Engineer: Real-Time Defect Detection Systems

Samsung Electronics America; Taylor (TX); On-site; USD 106,000 - 145,000; Full time

Benefits offered by this job

Onsite café

401(k) matching

Maternity/Paternity leave

PTO + holidays

Healthcare benefits

Job summary

Samsung Austin Semiconductor is seeking a Senior Machine Learning Engineer to lead ML initiatives in a high-throughput manufacturing environment. You will architect and deploy vision-based models for defect detection and classification, partner with module owners for domain-aligned modeling, and mentor a small team of engineers.

The role focuses on turning cutting-edge AI research into reliable production systems, with emphasis on performance, throughput, and maintainability in a 24/7 facility.

Qualifications

• BS or MS in Software Engineering, Computer Science, Data Science, Mathematics or related STEM/Engineering field.
• 5+ years relevant experience in ML/AI is required.
• Expertise with open-source ML frameworks (TensorFlow 2.x, PyTorch) and deploying models to production.

Responsibilities

• Architect advanced ML solutions for defect detection and classification.
• Drive domain alignment with module owners to translate defect characteristics into models.
• Innovate by researching AI advances and adapting architectures for manufacturing challenges.
• Optimize ML pipelines with feature engineering, tuning, and modern vision architectures.
• Ensure scalability for 24/7 production environments and mentor junior engineers.

Skills

Machine Learning

Python

Model Deployment

Statistical Modeling

Communication

Education

BS in Software Engineering/CS/Data Science/Mathematics

MS preferred

Tools

TensorFlow 2.x

PyTorch

Linux (Ubuntu)

Command Line Interfaces

Job description

Samsung Austin Semiconductor is seeking a Senior Machine Learning Engineer to lead ML initiatives in a high-throughput manufacturing environment. You will architect and deploy vision-based models for defect detection and classification, partner with module owners for domain-aligned modeling, and mentor a small team of engineers.

The role focuses on turning cutting-edge AI research into reliable production systems, with emphasis on performance, throughput, and maintainability in a 24/7 facility.