Pankaj Rajak

About Pankaj Rajak

My current research work is on the theory and application of reinforcement learning, generative models, geometric neural network such as graph network for inverse design of material with desired physical properties. Beside this, my research interest also includes meta-learning and current challenges in these models such as problems related to task-memorization in few-shot learning.Previously, during my PhD I worked on large scale molecular dynamics simulation of materials consisting of billions of atoms, uncertainty quantification, active learning for the synthesis of quantum materials, generative models such as variational auto-encoders and normalizing flows for 3-d point clouds of geometric objects and on problems related to relation extraction and named-entity recognition in natural language processing

Experience

1. Applied Scientist Ii

   Amazon

   Dec 2022 — Present

Education

• University of Southern California

  Master of Science - MS, Computer Science (specialization: Data Science)

  2016 — 2018

• Stanford University

  Artificial Intelligence Graduate Certificate

  2019 — 2021

• Indian Institute of Technology, Kharagpur

  Dual Degree: B.tec(Hons)+M.tec, Metallurgical and Materials Engineering

• University of Southern California

  Phd, Computational Materials Science

  2011 — 2018

Skills

• Scanning Electron Microscopy
• Sql
• Nanotechnology
• Algorithms
• Statistics
• Data Analysis
• C,C++,Java,Fortran,Html,Jsp,Servlet,Java Script,Sql,Matlab
• Machine Learning
• Python
• Simulations
• Mongodb
• Deep Learning
• Microsoft Excel
• Characterization
• C++
• Afm
• Materials Science
• Matlab
• Natural Language Processing
• C
• Microsoft Office