Using machine learning as a framework, we create models that help to reduce in the physical testing of products with Virtual Validation, predict the need for maintenance with Digital Twins, and ensure testing data informs the design of next generation products. we do this by creating hybrid models that are informed by engineering simulations and measurement data.

The impact machine learning and physics based simulations, together, will have on engineering product design and during the product life cycle is huge is just being recognized. I am working on models that combine physics- and data-based model for providing enhanced time-critical insights for engineers. I believe and have shown with my colleagues that measurements and models can work together in a symbiotic manner to provide critical information useful in conceptual design, virtual validation, and digital twins. I use simulations, surrogates, and measurement data as appropriate to deliver solutions that enhance the engineering workflows for our customers.

I spent my time developing solutions to enhance multiphase models to model all the flow regimes. In particular along with a few colleagues I spent time to develop models that address the issue of gas-liquid flows, and how one could model regime transitions.

As a lead technology specialist I was responsible for developing technology solutions in the area of Multiphase flow for our customers. I developed a high fidelity DEM code to enhance our offerings for multi-phase particulate flows. The dense DPM model was successful in addressing a wide variety of problems that spans across several flow regimes.

As a senior engineer I was responsible for developing and supporting technology solutions for our clients in the chemical, process, power and the oil and gas customers. I also developed solutions in Fluent that were generic and used across several Industries,

I was responsible for customer support, pre-sales demos and a marketing projects for the chemical, power, process and the oil and gas industries.