Saumik Dana, Ph.D.
Computational Engineer at Advanced Scanners- Claim this Profile
Click to upgrade to our gold package
for the full feature experience.
Topline Score
Bio
Experience
-
VISIE Inc., Formerly Advanced Scanners
-
United States
-
Medical Equipment Manufacturing
-
1 - 100 Employee
-
Computational Engineer
-
Aug 2023 - Present
→ Python code to interface with Kuka robot → Python code to interface with Kuka robot
-
-
-
Sapientai LLC
-
United States
-
Software Development
-
1 - 100 Employee
-
Computational Lead
-
Aug 2022 - Mar 2023
→ Developed a Python-based backend for a stock price prediction framework → Engineered a forecasting model through a process involving the discovery of a PDE for each stock price time series using a sparse regression greedy algorithm, XGBoost and Bayesian parameter optimization → Used autoregression analysis to establish the optimal window size for training the model → Exhibited exceptional generalization through comprehensive cross validation on the Kaggle stock market dataset → Collaborated with a ML engineer to conduct extensive unit testing and continuous delivery integration using GitHub Actions Show less
-
-
-
University of Southern California
-
United States
-
Higher Education
-
700 & Above Employee
-
Postdoctoral Research Associate
-
Nov 2020 - Jul 2022
→ Implemented a two-grid algorithm in a Python/C++ codebase with SWIG bindings, optimizing the compute time for large-scale grid problems by 50% → Utilized CMake to automate the build systems and conducted simulations on AWS EC2 instances → Created separate Python and C++ based codes for model parameter estimation from time series data using Bayesian inference → Diagnozed the performance of both MySQL and JSON in handling time series data interchange between the generation and inference modules → Utilized Markov chain Monte Carlo (MCMC) sampling using the Metropolis Hastings (MH) algorithm to infer model parameter distribution Show less
-
-
-
Baylor College of Medicine
-
United States
-
Higher Education
-
700 & Above Employee
-
Postdoctoral Research Associate
-
Feb 2020 - Oct 2020
→ Implemented algorithms for short and long read sequencing using Pythonic string manipulation libraries → Collaborated with biologists to develop user-friendly code for a forensics project → Implemented algorithms for short and long read sequencing using Pythonic string manipulation libraries → Collaborated with biologists to develop user-friendly code for a forensics project
-
-
-
Rensselaer Polytechnic Institute
-
United States
-
Higher Education
-
700 & Above Employee
-
Postdoctoral Research Associate
-
Aug 2019 - Jan 2020
→ Generated simulations of fluid flow to provide recommendations to a NYC based startup on design of a vertical axis wind turbine → Demonstrated a 20% power loss reduction through design improvements, focusing on the fillet region of the vertical axis wind turbine → Generated simulations of fluid flow to provide recommendations to a NYC based startup on design of a vertical axis wind turbine → Demonstrated a 20% power loss reduction through design improvements, focusing on the fillet region of the vertical axis wind turbine
-
-
-
Los Alamos National Laboratory
-
United States
-
Research Services
-
700 & Above Employee
-
Postdoctoral Research Associate
-
Jan 2019 - Jul 2019
→ Collaborated with scientists to integrate a Python wrapper that implements a graph theory based reduced order model for subsurface flow and transport → Traded 3D geometry for a graph-based reduced system that was 500-1000 times faster in terms of computational efficiency for this specific application → Showed that the reduced-order model has great potential for providing operators with real-time decision-making information for optimizing hydrocarbon production → Collaborated with scientists to integrate a Python wrapper that implements a graph theory based reduced order model for subsurface flow and transport → Traded 3D geometry for a graph-based reduced system that was 500-1000 times faster in terms of computational efficiency for this specific application → Showed that the reduced-order model has great potential for providing operators with real-time decision-making information for optimizing hydrocarbon production
-
-
-
Siemens
-
Germany
-
Automation Machinery Manufacturing
-
700 & Above Employee
-
Graduate Intern
-
Jun 2018 - Sep 2018
→ Collaborated with a staff scientist and product manager to develop a Python code for simulating temperature evolution in additive manufacturing microslices → Collaborated with a staff scientist and product manager to develop a Python code for simulating temperature evolution in additive manufacturing microslices
-
-
Education
-
The University of Texas at Austin
Doctor of Philosophy - PhD, Engineering Mechanics