Responsibilities:
- Design and implement end-to-end automated Modeling & Simulation workflows using an agentic AI interface.
- Develop frameworks to generate large, labeled synthetic datasets through parametric sweeps and DOE plans to enable rapid ML experimentation.
- Build and deploy machine learning surrogate models to provide fast, accurate performance predictions in place of full physics simulations
- Create inverse design methodologies that translate customer specifications into optimized product design solutions using surrogate models
- Significantly accelerate engineering workflows, reducing turnaround time from days to minutes while maintaining at least 90% validation accuracy against experimental data
- Integrate AI, simulation, and ML techniques to enhance product development efficiency and innovation.
- Present technical findings, insights, and performance outcomes effectively to engineering and management stakeholders.
Requirements:
- Proven experience in Artificial Intelligence, including Generative AI and Industrial AI, with strong knowledge of machine learning techniques applied to engineering data and simulations. This includes regression-based surrogate modelling and neural network architectures (e.g., CNNs, GNNs) suited for geometric and field-based data.
- Hands-on expertise in designing and deploying AI agents for industrial applications, with solid understanding of system architectures and automation frameworks.
- Deep experience in physics-based modelling and simulation, including preparation of simulation datasets for accelerated ML experimentation and development of ML surrogate models. Advanced proficiency in CFD and FEM tools such as Ansys, COMSOL, Abaqus, or open-source platforms like OpenFOAM is required.
- Strong programming capability in Python and/or C/C++, particularly for integrating with simulation software APIs and managing large-scale simulation outputs.
Account Manager:
Kerwin Tan Kai Bin (R1331624)
[Confidential Information]
EA16S8107
