Shrenik Z.
Graduate Research Assistant @Purdue University Mechanical Engineering
Signup · Get unlimited contacts
WORK HISTORY
Graduate Research Assistant @Purdue University Mechanical Engineering
West Lafayette, IN, US
Research Assistant at Predictive Science Lab- Developing a novel scalable Bayesian approach to causal discovery- Proposed a Bayesian calibration framework combining Gaussian processes with approximate Bayesian computation to build transferable probabilistic models for engine-out NOx- Integrated transformers with MPPI control to improve efficiency, reduce samples, and optimize autonomous navigation performance- Leveraged gated recurrent units for iterative online precise attitude control for geodetic missions- Used graph neural networks to model and predict engine-out NOx with a causal-enhanced gaussian process- Outperformed RNNs by 10% in learning engineered dynamics from noisy data using liquid time-constant networks- Built a predictive linear control oriented turbocharger turbine model using the Koopman operator approach- Developed innovative multiscale model combining atomistic simulations and machine learning to predict alloy behavior under high strain rate loads.
EDUCATION
Purdue University
Master of Science - MS, Mechanical Engineering
Purdue University
Doctor of Philosophy - PhD, Mechanical Engineering
Shiv Joyti Senior Secondary School
High School Diploma
Abu Dhabi Indian School
High School Diploma
Indian Institute of Technology, Madras
Bachelor of Technology, Naval Architecture and Marine Engineering
ABOUT SHRENIK Z.
I am looking for full time research roles in industry and academia starting Summer 2026.I am currently a final year PhD candidate in the School of Mechanical Engineering at Purdue University. I hold an undergraduate degree from the Indian Institute of Technology Madras, India.I have industry experience with RTX Technology Research Center and Mitsubishi Electric Research Laboratories as a Research Scientist. My research background lie in scientific machine learning, uncertainty quantification, causal AI, inverse problems, Bayesian statistics, digital twins, stochastic modeling, control, Gaussian processes, recurrent neural networks, graph neural networks and reinforcement learning. I have hands-on experience applying variety of techniques from my research to real-world systems such as internal combustion engines, hypersonic vehicles, refrigeration cycles, geodetic satellite missions and heave compensation. I am particularly interested in how mathematics and machine learning can work together to solve real world engineering problems.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.