AI-Driven Physical Design Engineering (PhD Intern)
Core
PhD intern developing AI/ML workflows and Graph Neural Networks to optimize physical design implementation for high-performance silicon.
Role type
PhD intern, AI-driven physical design engineer
Builds
AI-enhanced workflows for high-performance silicon implementation
Domain
Semiconductor / Physical Design / Machine Learning
Deliverable
production ML models
Required skills
Graph Neural Networks (GNN), Python, Machine Learning, Physical Design (synthesis, place and route, timing analysis), Digital Design (RTL, verification)
Preferred skills
Reinforcement Learning, Data Analysis (Pandas, NumPy, Matplotlib), EDA tools, Graph-based algorithms
Technologies
TensorFlow, PyTorch, TCL, Perl
Responsibilities
Research and implement AI/ML techniques for physical design processes; Develop AI-enhanced workflows to reduce manual effort; Build ML-powered data analysis pipelines; Design and implement GNN-based systems; Evaluate AI-driven methodologies against traditional approaches for PPA improvements
Seniority
PhD Intern
