- Collaborate with a cross-functional, multi-disciplinary team to identify new methodological approaches to layout analysis and define algorithmic solutions
- Develop software modules and shared libraries throughout a product life cycle, from prototype to customer release
- Implement testing and benchmarking automation for Pattern Analytics tools
- Coordinate the creation of engineering-level technical documentation for the supported products
- Troubleshoot and solve customer problems after deployment
- Stay updated with the latest advancements in EDA, data science, and machine learning to continuously enhance product offerings
The Impact You Will Have:
- Drive innovations in semiconductor design and silicon manufacturing flows through advanced pattern analytics
- Enhance the efficiency and accuracy of layout analysis methodologies, contributing to the overall improvement of EDA tools
- Facilitate the development of cutting-edge computational solutions that address critical gaps in current industrial solutions
- Ensure the successful deployment and adoption of new EDA products by providing robust technical documentation and customer support
- Contribute to the continuous evolution of Synopsys product offerings, maintaining our leadership in the industry
- Empower semiconductor companies and software developers with innovative tools that streamline design and verification processes
What You'll Need:
- Ph.D. or B.Tech/M.Tech in Electrical Engineering (EE), Computer Science (CS), or related fields, with a minimum of 5 years of industry experience
- Expertise in Python programming with a strong focus on data structures, advanced proficiency in libraries such as NumPy, Pandas, Matplotlib, Scipy, and development of new Python APIs or commands
- Extensive experience in C++ and/or Java
- Practical experience in developing Machine Learning models, including Graph Neural Network (GNN) models and LLM's type of models
- Knowledge in probability and statistics, Electronic Design Automation (EDA), VLSI Physical Design Verification, and/or Mask Data Generation
