Intern - Planning IE Posted 10 hours ago

Our vision is to transform how the world uses information to enrich life for all.

Join an inclusive team passionate about one thing: using their expertise in the relentless pursuit of innovation for customers and partners. The solutions we build help make everything from virtual reality experiences to breakthroughs in neural networks possible. We do it all while committing to integrity, sustainability, and giving back to our communities. Because doing so can fuel the very innovation we are pursuing.

Agentic AI–Driven Intelligent Planning Ecosystem for Fab Space and Capacity Optimization

This internship project focuses on the development of an Agentic AI-enabled planning ecosystem to enhance fab space utilization, tool placement planning, and decision-making across the Planning (PLN) domain. The intern will have the opportunity to contribute to the design and evaluation of an intelligent multi-agent framework that supports planning optimization through data-driven analysis and Artificial Intelligence technologies.

• Industrial Engineering (IE) Agent for tool demand forecasting and capacity planning
• Layout Agent for space allocation analysis and constraint evaluation
• Material and Spare Planning Agent for resource planning optimization
• Operations Modelling Agent for scenario simulation and planning insights
• Cost/Capex Agent for investment and cost optimization assessments

Through collaboration with planning stakeholders, the intern will gain exposure to AI-enabled planning methodologies, multi-agent reasoning frameworks, optimization techniques, and large-scale manufacturing planning challenges.

The objective of this project is to evaluate how Agentic AI solutions can improve planning effectiveness by enabling coordinated decision-making across multiple planning domains. The project aims to identify opportunities to optimize fab capacity utilization, improve planning alignment, and enhance future-state scenario evaluation through intelligent agent collaboration.

Successful completion of the internship may provide opportunities to be considered for future full-time roles, subject to business requirements, performance, and available openings.

The intern will have opportunities to:

• Study existing planning workflows and data inputs across the PLN domain.
• Develop proof-of-concept Agentic AI workflows for planning optimization.
• Evaluate coordination mechanisms between multiple specialized AI agents.
• Analyze planning trade-offs involving tool demand, factory layout constraints, material requirements, operational scenarios, and capital investment considerations.
• Explore AI-Enabled approaches for generating planning recommendations and scenario-based decision support.
• Document findings, recommendations, and improvement opportunities.

The intern will gain hands‑on experience in:

• Agentic AI and multi-agent system design
• Generative AI and Large Language Model (LLM) applications
• Manufacturing planning and capacity optimization methodologies
• Operations research and optimization techniques
• Data analytics and scenario modelling
• AI-enabled decision support systems
• Cross‑functional collaboration within semiconductor manufacturing environments

• Agentic AI planning ecosystem proof-of-concept or prototype
• Multi-agent workflow design documentation
• Planning optimization analysis and scenario evaluation results
• Recommendations for space utilization, tool placement, and planning improvements
• Final project presentation summarizing findings and future enhancement opportunities

This project aims to demonstrate how Agentic AI technologies can contribute to improved planning effectiveness by enabling coordinated, data-driven decision-making across multiple planning functions. The outcomes may provide insights into space optimization opportunities, planning efficiency improvements, and scalable approaches for future intelligent planning ecosystems.

• Programming experience in Python, Java, or similar languages
• Knowledge of data analytics, statistics, or optimization techniques
• Familiar…