Production ML Engineer: Anomaly Detection & PySpark Pipelines

Samsung; Taylor (TX); On-site; USD 90,000 - 175,000; Full time

Benefits offered by this job

Medical, dental, and vision insurance

401(k) matching with immediate vesting

Onsite café and workout facilities

Paid maternity and paternity leave

PTO + 2 personal holidays and 10 fixed

Wellness incentives and MORE

MBO bonuses based on performance

Job summary

Samsung Austin Semiconductor in Taylor, TX is seeking a Machine Learning Engineer to build and maintain production ML pipelines for anomaly detection and root cause analysis on onsite infrastructure. You will develop PySpark workflows to ingest and transform high-volume manufacturing data, optimize Spark performance, and deploy end-to-end ML pipelines with reproducible runs and auditable results.

Strong experience with PySpark, distributed data processing, Python ML libraries, and MLOps is

Qualifications

• Bachelor’s degree or higher in a quantitative field.
• 3-5+ years of experience building and maintaining ML systems.
• Strong PySpark and distributed data processing skills.

Responsibilities

• Develop PySpark workflows to ingest, clean, and transform high-volume data.
• Tune Spark performance: partition strategies, memory, and joins.
• Create end-to-end ML pipelines with reproducible runs and auditable results.
• Build models for anomaly detection and root cause analysis.
• Manage production model lifecycle, versions, retraining, and rollbacks.
• Monitor pipeline timings, data quality, and model metrics with alerts.

Skills

PySpark

Distributed data processing

Python ML libraries

MLOps

Monitoring and alerting

Education

Bachelor’s degree or higher in CS/SE/Data Science

Tools

Spark

Python

scikit-learn

TensorFlow

PyTorch

XGBoost

Job description

Samsung Austin Semiconductor in Taylor, TX is seeking a Machine Learning Engineer to build and maintain production ML pipelines for anomaly detection and root cause analysis on onsite infrastructure. You will develop PySpark workflows to ingest and transform high-volume manufacturing data, optimize Spark performance, and deploy end-to-end ML pipelines with reproducible runs and auditable results.

Strong experience with PySpark, distributed data processing, Python ML libraries, and MLOps is