Machine Learning Engineer, Quality Analytics

We are seeking a versatile and hands-on Machine Learning Engineer to join our Quality Analytics team. You will be a critical bridge between data science and engineering, responsible for the development of machine learning solutions that solve real-world manufacturing challenges. You will leverage your expertise in statistical analysis, general machine learning, and software engineering to build and deploy robust models for predictive quality, yield optimization, anomaly detection, and root cause analysis. You will work within existing business systems (ERP, MES, Inventory Management, Warehouse Management, Quality Incident management system and QMS systems) to build, maintain, and improve the data analysis. Your work will directly contribute to improving product quality, reducing waste, and increasing operational efficiency on our factory floor. This role combines AIML model development with data pipeline development with deep-dive investigation into data quality as it relates to manufacturing quality.

WHAT YOU’LL DO

• Design, build, deploy, and maintain machine learning models to address key manufacturing problems, including classification (e.g., defect type), regression (e.g., yield prediction), and clustering (e.g., process regime identification).
• Perform in-depth exploratory data analysis (EDA) and statistical analysis on complex manufacturing datasets (sensor data, MES records, quality logs) to uncover insights and validate hypotheses using Python, Pandas, Scikit-learn, and Jupyter notebooks.
• Develop and implement computer vision models for automated visual inspection and defect identification where applicable.
• Partner with the Data Engineers to operationalize models within Palantir Foundry, creating scalable and automated training and inference pipelines.
• Implement MLOps best practices for version control, model monitoring, performance tracking, and automated retraining to ensure long-term model health and reliability.
• Collaborate closely with Manufacturing Engineers and Data Analysts to understand process nuances, define model requirements, and interpret results for non-technical stakeholders.
• Translate complex manufacturing problems, such as sources of variance or defect trends, into solvable machine learning problems.

REQUIRED QUALIFICATIONS

• Bachelor’s or Master’s degree in Computer Science, Engineering, Statistics, or a related quantitative field.
• 3+ years of experience in an ML Engineer, Data Scientist, or similar role with a proven track record of deploying models into a production environment.
• Demonstrated experience working within a manufacturing, industrial, robotics or other physical environment is essential.
• Strong proficiency in Python and core data science libraries (Scikit-learn, Pandas, NumPy, Matplotlib/Seaborn).
• Solid understanding of both classical machine learning algorithms (e.g., Gradient Boosting, Random Forest, SVMs) and fundamental statistical principles.
• Hands-on experience with SQL for data extraction and manipulation.
• Experience with the complete ML lifecycle, from data exploration and feature engineering to deployment and monitoring.
• Eligible to obtain and maintain an active U.S. Secret security clearance.

PREFERRED QUALIFICATIONS

• Experience with deep learning frameworks (e.g., TensorFlow, PyTorch), particularly for computer vision applications.
• Experience with big data platforms like Palantir Foundry or Databricks.
• Knowledge of MLOps tools and principles (e.g., MLflow, Kubeflow, model registries).
• Familiarity with manufacturing data systems (e.g., MES, SFC, ERP).
• Familiarity with quality methodologies and concepts like RCCA or 8D, GD&T, FMEA, IQC/OQC, and how data supports them.
• Strong software engineering fundamentals, including experience with Git.
• Experience building or supporting ML cababilities for complex hardware manufacturing operations, including new product introduction (NPI), ramp-up, and high-volume production phases.