Associate Data Scientist/Data engineer with over 4.3 years of experience in Data Science, Analytics, and Enrichment. Proficient in Python and libraries including Pandas, NumPy, Scikit-learn, TensorFlow, and Seaborn. Skilled in Snowflake and FosFor for delivering successful automation projects. Experienced with tools such as Jupyter Notebook, Visual Studio, and CDSW.
Overview
4
4
years of professional experience
1
1
Certification
Work History
Data Engineer
LTIMINDTREE (Client)
Noida
05.2023 - Current
Collaborated effectively by utilizing expertise in working with a wide range of Large Language Models (LLMs) including Snowflake-Cortex, OpenAI, LAMA2, and Gemini.
Executing prompt engineering to create model submissions on time.
Utilized k-means clustering in developing an application for customer categorization based on RFM (Recency, Frequency, Monetary) analysis using the appropriate technology and tools.
Created a user-friendly Streamlit app that utilizes OpenAI/Cortex to generate synthetic data tables from table metadata.
Independently developing a Streamlit application to generate GenAl emails using given prompts.
Associate Data Scientist
Client- (Finance Intelligence Unit) | LTIMindtree
New Delhi
11.2022 - 04.2023
Utilized advanced data modeling techniques to enhance system performance by reducing processing time by 15%.
Collaborated with cross-functional teams to analyze business requirements and design data models matching organizational goals
Successfully implemented a data-driven approach utilizing machine learning algorithms to assess vast amounts of categorical data, resulting in an impressive 20% boost in predictive accuracy for customer reports.
Leveraged natural language processing techniques to extract valuable information from unstructured data, facilitating sentiment analysis and customer sentiment tracking.
Associate Data Scientist
Client - Project Insight (Central Board of Direct Taxes, Government of India) | LTIMINDTREE
07.2021 - 10.2022
Managed client interactions in an agile environment while actively collaborating with Income Tax officials to comprehend and adapt to their business requirements
Processed and analyzed large data from multiple jurisdictions globally, involving key steps such as data retrieval, cleansing, exploratory analysis, feature engineering, selection, and imputation using Python and SQL.
Applied data pre-processing methods for standardizing PAN-specific information (address, phone numbers, emails) gathered from various sources.
Identified ways to optimize data extraction, processing, and cleanup procedures while resolving technical issues
Enhanced table efficiency by reducing bias through effective data analysis techniques, proper indexing, and optimized join conditions, leading to a remarkable 35% improvement in overall performance
Executed joint initiatives with Airtel targeting around 12 million taxpayers/entities for a specific year that generated a tax revenue of Rs.3000 crore
Associate Data Scientist
Client - Ministry of corporate affairs, Government of India | LTIMINDTREE
01.2020 - 07.2021
Developed 20+ use cases/approach for sentiment analysis, NER, word cloud, risk profiling, and summary generation
Processing master data and applying feature selection algorithms to categorize comment sentiments
Applied Unsupervised Learning Algorithms for Clustering to enhance risk score retrieval and boost performance by 30-40%
Utilized NLP technique to extract summary for comments and enhancements using NER and Pre-Trained summarization algorithm
Streamlined operations by utilizing the integrated capabilities of Cloudera data science workbench for scheduling, monitoring, and email alerts.
Education
Bachelor of Technlogy - Information Technology
National Institute of Science and Technology, Odisha
01.2019
Skills
Python
SQL, Teradata
Pandas, NumPy, Sklearn, TensorFlow, Sea-born
NLP, NER
Machine learning
Generative AI, LLM ,Prompt Engineering
AWS, Snowflake, Cloudera data science workbench, FosFor
Jupyter Notebook, Visual Studio
Data analysis, Data cleansing, Data Modelling
SAS
WinScp, Excel
GitHub
Certification
Python Programming using Data science from Udemy
Generative AI Fundamentals from DataBricks
Accomplishments
Winner of Phoenix(L) (Transformation) for Q4FY22 edition of GoMx awards
Timeline
Data Engineer
LTIMINDTREE (Client)
05.2023 - Current
Associate Data Scientist
Client- (Finance Intelligence Unit) | LTIMindtree
11.2022 - 04.2023
Associate Data Scientist
Client - Project Insight (Central Board of Direct Taxes, Government of India) | LTIMINDTREE
07.2021 - 10.2022
Associate Data Scientist
Client - Ministry of corporate affairs, Government of India | LTIMINDTREE
01.2020 - 07.2021
Bachelor of Technlogy - Information Technology
National Institute of Science and Technology, Odisha
Secondary Track Lead — Solace at LTIMindtree (Client - Citi Bank ICG & PBWM)Secondary Track Lead — Solace at LTIMindtree (Client - Citi Bank ICG & PBWM)