I began my journey with computers in 2009, developing exceptional problem-solving skills and a knack for crafting effective solutions. Over the years, I’ve built a career as a results-driven data scientist with extensive expertise in machine learning, deep learning, and AI solutions, spanning impactful roles across startups, enterprises, and regulated industries.
With over 10 years of experience spanning early-stage startups (4) and Fortune 500 companies, I aim to combine innovation with impact.
Featured in Topmate.io’s Top 100 Data Coaches
Mentored graduate students and other Data Science and AI Professionals via Topmate and WIDS
Co-authored a paper, “ Bayesian Iterative Prediction and Lexical-based Interpretation for Disturbed Chinese Sentence Pair Matching,” published in the ACM proceedings
Published Article Tools and Frameworks for Deep Learning CPU Benchmarks
Technical Reviewer at Technical Reviewer at AdSoc5.0 (2025)
Are you a startup or company looking to accelerate your product development and outpace the competition? Let’s connect!
MS in Computer Science
The University of Texas at Dallas
B.Tech in Metallurgical Engineering
National Institute of Technology, Raipur
Capital One Financial Corporation is an American bank holding company specializing in credit cards, auto loans, banking, and savings accounts operated primarily in US.
• Model Impact: Achieved six-figure cost savings by eliminating vendor, supporting critical usage such as CCAR compliance, NII sensitivity, AOCI forecasting, trading analytics, pricing, and Interest rate risk management.
• Deep Learning Explainability Tool: Enhanced model transparency by equipping stakeholders with insights to support key business decisions through a web application utilizing explainability method.
• Model Monitoring: Led the implementation of monitoring systems to track performance and ensure compliance, providing insights to stakeholders to support business decisions and stay compliant.
Capital One Financial Corporation is an American bank holding company specializing in credit cards, auto loans, banking, and savings accounts operated primarily in US.
• Feature Engineering: Partnered with domain experts and stakeholders to define strategic objectives for the MBS prepayment model, performing feature engineering and exploratory data analysis to identify key predictors of prepayment behavior.
• Data Engineering: Played key role in designing a robust data pipeline, collaborating with the data team to integrate dynamic and static features, ensuring streamlined workflows for training and production.
• Model Training and Communication: Leveraged deep learning expertise to train high performance models, collaborating with the risk management team to deliver insights and secure approvals.
Ocrolus is a document automation platform that powers the digital lending ecosystem, automating credit decisions across fintech, mortgage, and banking.
• Debugged and validated the data pipeline to develop a model for classifying businesses into categories for loan processing.
Lantern Pharma is a uniquely positioned life science company pushing innovations in pharmaceutical biotechnology and drug-companion diagnostic co-development through Artificial Intelligence, Machine Learning, and Genomics.
• Developed a module to ingest genomics data (TCGA) of 50k+ samples and 3 billion+ data points into S3 using Nextflow, a workflow management system for bioinformatics analysis.
• Implemented a micro-service using Docker to process the ingested data, and deployed it using AWS ECS (Elastic Container Service) for scalability and fault tolerance
Capital One Financial Corporation is an American bank holding company specializing in credit cards, auto loans, banking, and savings accounts operated primarily in US.
• Optimized workflow to reduce experimentation time, and generated a comprehensive report for POC models’ comparison.
VHSS Lab, UTD is a cross-disciplinary team including full-time and student computer and behavioral scientists, human computer interaction experts, animators and modelers under Dr. Marjorie Zielke.
Researched and trained transformer-based model for (virtual patient)[https://news.utdallas.edu/science-technology/augmented-reality-zielke-nsf-grant-2020/?WT.mc_id=NewsEmail] interacting with medical students using Pytorch.
Huddl is the collaboration hub that brings the right people, information, and tools together to get work done.
• Led development of an NER system for a voice assistant, utilizing gazetteer to improve accuracy. • Built an OCR parser with K-means clustering to filter keywords for improving search results of meeting screenshots.
CoArtha TechnoSolutions is an IT company and has a product called maprecruit.com which provides a parallel and intelligent recruiting platform.
• Built an NER system to map entities from job descriptions and resumes into a Knowledge Graph, enhancing matching and ranking performance.
• Developed a Random Forest model to assess candidates, leveraging audio features and transcription.
CoArtha TechnoSolutions is an IT company and has a product called maprecruit.com which provides a parallel and intelligent recruiting platform.
• Built a pipeline to scrape data from 1M+ job descriptions, engineered features, and trained a classifier for sections.
Motivated by my previous training experience at DSIM, We started a small venture, Digifledged. Here, We started a small venture to help businesses to start their digital journey. We mainly served services such as web development, digital marketing, Analytics using machine learning, and excel automation/reporting projects services with macros.
Responsibilities:-
Client Projects:- Projectcuriosity.in | Ophthalmicmart.com(old) | Aditispat.com | Ezoneservices.in
JSW Group is a $12 billion company and leading Indian multinational steel making company. It is one of the fastest growing companies in India with a global footprint in over 140 countries
• Managed a sub section of manufacturing area and provided analysis to upper management, resulting in productivity improvement.
Linear/Logistic Regression, SVM, Clustering, Tree Algorithms, Naive Bayes, Ensemble Methods
Numpy, Pandas, Matplotlib, Plotly, NLTK, Gensim, Sklearn, Spacy, Scipy, Tensorflow, PyTorch
Feed Forward NN, RNN, CNN, Attention Mechanism
MySQL, MongoDB, ElasticSearch, DynamoDB, Neo4j
Linux, Django, Rest-API, Docker, Kubernetes, ML-flow, AWS, Terraform, ECR, Hadoop, Hive, Spark
Python, C, Java, Scala, Matlab, Django, Flask, Node.js