About Me

Alfin-Headshot

Results-driven Data Professional actively developing predictive ML applications alongside 1.5+ years of applied experience architecting scalable data pipelines, deploying predictive ML models, and delivering actionable BI insights.

Drove revenue and optimized workflows by processing 2M+ records using Python, SQL, and AWS.

Work Experience

Dreamline AI

Data Analyst @ Dreamline AI

Aug 2025 - Feb 2026
Wethersfield, CT, USA (Remote)

  • Built automated web scraping pipelines using Scrapy and Playwright to collect property ownership data from 67 Florida counties, reducing manual data collection time by 80% (from 30 to 6 hours/week).
  • Processed and validated 2M+ property records through standardized data cleaning workflows, identifying 250K+ high-value prospects and enabling targeted marketing decisions for customer acquisition.

Community Dreams Foundation

Data Analyst @ Community Dreams Foundation

Sep 2024 - Aug 2025
Wethersfield, CT, USA (Remote)

  • Designed and implemented a scalable synthetic data pipeline to train CDF's in-house, ML-powered resume analyzer, enhancing data quality across 35+ job profiles with a focus on industry trends, role relevance, and privacy compliance.
  • Leveraged LLMs (ChatGPT-4o, Claude 3.5 Sonnet) with custom prompt engineering to generate realistic, role-specific resumes, enabling high-accuracy model performance (96.2%) and ultimately improving HR workflows.

Indian Institute of Technology Indore

Machine Learning Researcher @ Indian Institute of Technology Indore

Jan 2022 - Mar 2022
Indore, MP, India

  • Developed advanced Gaussian Process Regression models with Rational Quadratic and Exponential kernels to forecast peak solar irradiance (solar power potential) from complex historical time-series data, achieving 83% prediction accuracy.
  • Led end-to-end data preparation, including cleaning, outlier handling, and feature optimization using Python (Pandas, Scikit-learn, NumPy), and validated model reliability through RMSE evaluation and 95% confidence intervals.
  • This work contributed to improving solar panel efficiency to maximize energy yield.

Education

Seattle University

MSCS Data Science Specialization @ Seattle University

Sep 2022 - June 2024
Seattle, WA, USA
Awards: Dean's Graduate Student Honor Roll

Coursework: Machine Learning, Artificial Intelligence, Visual Analytics, Cloud Computing, Social Media Analytics, Software Testing & Debugging, Ethics & Professional Issues in Computing

Medicaps University

B.Tech. Computer Science & Engineering @ Medicaps University

Sep 2018 - May 2022
Indore, MP, India
Awards: First Division with Honours

Coursework: Operating Systems, Computer Networks, Software Engineering, Compiler Design, Python Essentials, Machine Learning, Natural Language Processing, Artificial Intelligence

My Projects

Skills

Python HTML CSS Tailwind CSS Bootstrap pytest Selenium C Microsoft Excel Tableau Desktop Microsoft Power BI Docker Desktop AWS EC2 AWS S3 AWS RDS AWS DynamoDB AWS Aurora AWS Lambda AWS SageMaker AWS QuickSight MySQL PostgreSQL Machine Learning Statistical Data Modeling Prompt Engineering Data Visualization GitHub Visual Studio Code PyCharm Visual Studio Atom Postman

Languages

English (Fluent) Hindi (Native) Malayalam (Native)

Hit Me Up!