Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am a graduate student specializing in data science, machine learning, and statistical analysis, with hands-on experience performing EDA, building predictive models, engineering features, and processing large datasets using Python, Pandas, NumPy, and PySpark. I have a strong background in data modeling, data cleansing, and analytics workflows, and I enjoy communicating insights through visualizations and reports. I also have practical exposure to unstructured-data parsing, vector search, and AI-assisted document analysis, and I am excited to support customer attrition modeling and analytics workflows.…I am a graduate student specializing in data science, machine learning, and statistical analysis, with hands-on experience performing EDA, building predictive models, engineering features, and processing large datasets using Python, Pandas, NumPy, and PySpark. I have a strong background in data modeling, data cleansing, and analytics workflows, and I enjoy communicating insights through visualizations and reports. I also have practical exposure to unstructured-data parsing, vector search, and AI-assisted document analysis, and I am excited to support customer attrition modeling and analytics workflows.

Soumik Mitra

Developer, AI Prompt Engineer, Web Developer, +6





I am a graduate student specializing in data science, machine learning, and statistical analysis, with hands-on experience performing EDA, building predictive models, engineering features, and processing large datasets using Python, Pandas, NumPy, and PySpark. I have a strong background in data modeling, data cleansing, and analytics workflows, and I enjoy communicating insights through visualizations and reports. I also have practical exposure to unstructured-data parsing, vector search, and AI-assisted document analysis, and I am excited to support customer attrition modeling and analytics workflows.…I am a graduate student specializing in data science, machine learning, and statistical analysis, with hands-on experience performing EDA, building predictive models, engineering features, and processing large datasets using Python, Pandas, NumPy, and PySpark. I have a strong background in data modeling, data cleansing, and analytics workflows, and I enjoy communicating insights through visualizations and reports. I also have practical exposure to unstructured-data parsing, vector search, and AI-assisted document analysis, and I am excited to support customer attrition modeling and analytics workflows.

Available to hire

I am a graduate student specializing in data science, machine learning, and statistical analysis, with hands-on experience performing EDA, building predictive models, engineering features, and processing large datasets using Python, Pandas, NumPy, and PySpark.

I have a strong background in data modeling, data cleansing, and analytics workflows, and I enjoy communicating insights through visualizations and reports. I also have practical exposure to unstructured-data parsing, vector search, and AI-assisted document analysis, and I am excited to support customer attrition modeling and analytics workflows.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Language

English

Advanced

Work Experience

Data Engineer and Analyst at Central Bank of India

July 1, 2025 - September 19, 2025

Developed and deployed end-to-end ETL pipelines using IBM DataStage to extract and transform six months of housing loan data across multiple relational tables. Re-engineered the same pipeline using Apache PySpark, implementing joins, aggregations, and transformations; achieved 3x faster performance over DataStage. Conducted feature extraction and exploratory data analysis (EDA) using Jupyter Notebook to uncover trends in customer housing loans and associated profits. Integrated pipeline outputs with Oracle Sandbox (via DataStage) and HDFS (via PySpark) for scalable data storage and team-wide accessibility. Ensured data security and confidentiality in alignment with banking compliance requirements; generalized findings for internal reporting.

SysOps Technician at University of South Carolina Aiken

May 1, 2025 - September 19, 2025

Utilized PDQ Smart Deploy to streamline Windows OS imaging and deployment across multiple workstations, reducing setup time and ensuring consistency. Provided tier-1 and tier-2 technical support, diagnosing and resolving hardware failures, software conflicts, network connectivity issues, and security concerns. Installed and configured Windows-based systems, including setting up user profiles, applying security policies, and installing necessary drivers and enterprise applications. Managed IT asset inventory using tracking software, ensuring accurate documentation of deployed systems and improving resource allocation.

SOC Analyst at University of South Carolina Aiken

August 1, 2024 - September 19, 2025

Investigated and mitigated a campus-wide phishing attack involving malicious .docx attachments, affecting nearly 90% of users. Analyzed security alerts using Microsoft Azure, tracked the origin of phishing emails, and identified compromised accounts. Used Palo Alto Firewall to detect and block malicious traffic; Cisco Meraki to pinpoint affected devices; SolarWinds to submit incident reports and escalate unresolved threats. Monitored system logs with Graylog to detect anomalies and support remediation.

Math Tutor at University of South Carolina Aiken

May 1, 2025 - September 19, 2025

Provided one-on-one and group tutoring in Algebra, Calculus, and Trigonometry; tutored over 700 students, improving academic performance. Created 100+ practice sheets to support learning and independent practice. Adapted teaching strategies to diverse learning styles and maintained clear communication with students, faculty, and academic support staff.

Data Engineer Intern at Central Bank of India

August 1, 2025 - August 1, 2025

Engineered end-to-end ETL pipelines using IBM DataStage and Python; optimized Apache PySpark pipelines with joins, aggregations, and transformations to achieve ~3x faster performance. Performed exploratory data analysis in Python with Jupyter Notebook to identify trends in loan approvals, defaults, and profitability. Integrated processed data with Oracle Sandbox and HDFS to enable scalable storage and seamless access. Collaborated with cross-functional teams using Agile methodologies, Git, and JIRA to facilitate code reviews and version control.

Android App Developer at University of South Carolina Aiken

March 1, 2024 - March 1, 2024

Designed and developed an Android application for discrete mathematics using Java and XML in Android Studio; achieved 100+ downloads in the first month; collaborated with Dr. Rao Li on UI via Figma; integrated Google Ads API and a PDF library; published on Google Play Store in March 2024; practiced Agile with bi-weekly sprints; used Git to manage codebase.

Frontend Developer - Knowledge Hub (PWA) at University of South Carolina Aiken

November 1, 2024 - November 1, 2024

Developed a Progressive Web Application using React with TypeScript and Vite, enabling offline access for seamless PDF reading; implemented bookmarking, last-read scrollable section, and search; integrated Material UI and responsive design for desktop and mobile.

Full-Stack/Frontend Developer - Personal Finance Dashboard at Independent Project

September 1, 2025 - November 4, 2025

Built a full-stack application with Vite + React + TypeScript frontend and Express.js + Prisma ORM backend; persisted expenses in MySQL; implemented JWT authentication and bcrypt hashing; designed dark UI with Tailwind CSS; created custom React Hooks for grouping transactions; visualized spending trends with Chart.js; containerized with Docker and automated build checks with GitHub Actions for CI/CD.