Data Scientist at Cognitiv.ai
I am a Data Scientist with over 4 years of experience, currently designing and implementing machine learning solutions in the Ad Tech space at Cognitiv.ai. Previously, I worked with Apple and Gartner, where I drove impactful, data-driven solutions across the services domain.
I hold a Master’s degree in Electrical Engineering, specializing in Machine Learning and Data Science, from the University of California, San Diego, and a Bachelor’s degree in Electrical Engineering from the Indian Institute of Technology (BHU), Varanasi.
Some events that led to where i am right now.
Major : Machine Learning and Data Science September '2022 - March '2024
Relevant Courses : ECE 225A: Prob & Stats for Data Science ECE 143: Programming for Data Analysis CSE 256: Statistical NLP ECE 251B: Neural Networks / Pattern Recognition ECE 271A: Statistical Learning DSC 291 : Algorithms for Data Science
Major : Electrical Engineering July '2015 - July '2019
Relevant Courses : Distributed Computing, Introduction to High Performance Computing, Parallel Computing, Numerical Techniques, Discrete Mathematics, Numerical Techniques
April '2024 - Present
My projects focus on applying machine learning and statistical modeling to drive improvements in key performance metrics and conducted A/B testing to enhance model outcomes. Additionally, I also developed scalable data pipelines and implemented automation solutions to streamline and optimize predictive modeling processes.
June '2023 - September' 2023
At Apple, I interned with the Ads Platform Data Insights Team, where I played a pivotal role in analyzing the impact of predictive models on advertiser selection, creating data pipelines for log processing, and presenting actionable insights to cross-functional teams. My contributions led to significant cost savings and improved data utilization across the organization.
June '2019 - June' 2022
At Gartner i worked with the Data Science team at their Gurgaon office. I have worked on various projects including creating a multiclass comment classifier. I also worked on creating a recommendation engine that would suggest the next steps for the clients based on digital footprints of them as well as their peers.
May '2018 - July '2018
Trained and tested various supervised algorithms like Random Forest, Naïve Bayes and SVM using TF- IDF feature vectors to create a new FILTER in the tool achieved a classification accuracy of 83%. I also worked on automating the process of report generation using python that brought down the time spent from 15 hours per week to 2 hours .
May '2017 - July '2017
Worked under the guidance of Dr S. Sumitra. Here i developed a framework to capture the meaning of an unknown word by leveraging its root word and suffix through word embeddings. Also implemented Markov Chain Monte Carlo on UC Irvine Machine Learning Repository to achieve a macro- average precision of 91% over 11 classes.
Sep '2022 - Dec' 2022
As a part of course project for ECE 143, worked in a team of 4 to a dashboard to track global CO2 level and determine its correlation with different geographical, ecnonomical and political factors. Git Repo
Sep '2022 - Dec' 2022
Created a custom CUDA Kernel to perform Matrix Multiplication and ReLU activation function and use pybind11 to import kernels into python for inferencing model evaluation. Git Repo
Jan '2019 - April' 2019
Worked in a team of 4 to implement Key point – based Deformable Model (K3DM) algorithm using parallel computing that automatically establishes dense correspondences across many 3D faces and achieved a turnaround time of 1.42 seconds compared to 26.97 seconds when implemented serially
Jul '2018 - Dec '2018
Worked in a team of 3 to study the effects of memory and communication bottlenecks via direct measurement of time and energy. Used MPI (Message Passing Interface) to create programs to run across multiple systems and used the NAS parallel Benchmark (NPB) to evaluate the performance.