PhD candidate in computational mechanics and scientific machine learning at City, St George's, University of London. I build transparent computational tools for fracture and damage mechanics, with a focus on differentiable simulation, GPU computing, inverse problems, and engineering applications of AI.
Portfolio 路 PhAST documentation 路 Google Scholar 路 LinkedIn 路 Email
- PhAST: a public PyTorch-native, GPU-accelerated differentiable physics engine for phase-field fracture. The associated arXiv preprint presents the formulation, numerical benchmarks, and inverse-analysis examples. Source code
- Machine learning for computational fracture and damage mechanics: lead-authored review in Engineering Fracture Mechanics (2026), with collaborators at EPFL, the University of Florida, and City St George's.
- Open tutorials: runnable material on PyTorch, neural operators, physics-informed neural networks, and their computational-mechanics context. I created these while assisting Dr Sathiskumar Anusuya Ponnusami's teaching at Queen Mary University of London.
Before doctoral research, I founded Aeroknacks and developed aerospace structural-analysis and hand-calculation automation tools. This work translated established references, including E. F. Bruhn, Michael Niu, Boeing Design Manuals, and ESDU data, into practical Excel-VBA and engineering-software workflows.
I hold an MTech in Design and Manufacturing from the National Institute of Technology Silchar and a B.E. in Mechanical Engineering from Visvesvaraya Technological University.