What are the responsibilities and job description for the Thermal Engineering R&D Intern position at Advantest?
Description:
We are seeking a motivated engineering intern to support the development of an AI/ML-driven system for thermal monitoring, prediction, and anomaly detection during semi-conductor tests. The intern will focus primarily on machine learning model development and evaluation, data analysis, model experimentation, and software implementation, working with thermal system telemetry data to identify optimal modeling approaches.
Responsibilities
- Model Development & Prototyping: Research, develop, and test ML models (Regression, Time-Series, Anomaly Detection) using Python frameworks like TensorFlow, PyTorch, or Scikit-learn to improve thermal monitoring and prediction.
- Data Engineering & Pipeline Support: Build and automate data pipelines, including preprocessing, feature engineering, and labeling of thermal telemetry data for model training.
- Validation & Benchmarking: Conduct simulation-based validation and performance benchmarking to compare algorithms, ensuring model accuracy against real-world measured system behavior.
- Telemetry Analysis & Visualization: Analyze and visualize large datasets to identify patterns and performance anomalies, helping refine predictive capabilities.
- Hardware & Systems Integration: Collaborate with cross-functional engineering teams to acquire system logs, configure test setups, and integrate ML models into the broader software architecture.
- Documentation & Reporting: Maintain clear documentation of model assumptions, training methodologies, and results to support future model selection and deployment.
Qualifications:
Requirements & Qualifications
- Education: Currently pursuing a degree in Computer Science, Data Science, ME, EE, or a related field, with relevant coursework in AI/ML.
- Technical Proficiency: Strong Python skills, specifically using the data science stack (NumPy, Pandas, Scikit-learn, TensorFlow, or PyTorch) and visualization tools like Matplotlib.
- Domain Knowledge: Familiarity with time-series analysis, anomaly detection, or predictive modeling; an understanding of thermal behavior, physical sensors or control systems is a plus.
- Data Workflow: Experience managing scientific computing workflows within Jupyter environments, including data cleaning and performance evaluation.
- Professional Attributes: A curious, analytical mindset with the ability to collaborate across engineering teams (Software, Thermal, Systems) and clearly document technical findings.
Preferred Skills
- Strong analytical and problem-solving mindset with the ability to work with data and evaluate model performance.
- Minimal travel may be required (typically <5%).