Amrith Purandhar

Data Scientist

Karnataka, India 5+ yrs exp 90 · Outstanding

About

Data Scientist with 4+ years of overall IT experience, including 3+ years specializing in machine learning, data analysis, and AI. Experienced in building classification and regression models, developing RAG pipelines with LLMs, and deploying production ML solutions on AWS. Strong foundation in EDA, feature engineering, model evaluation, and data visualization, with hands-on experience in end-to-end ML productionization using Docker, CI/CD, and cloud platforms.

Skills & Expertise (30)

scikit-learn Advanced

8.5/10

Years Exp

Python Advanced

8.5/10

Years Exp

Pandas Advanced

8.0/10

Years Exp

NumPy Advanced

8.0/10

Years Exp

XGBoost Advanced

8.0/10

Years Exp

LightGBM Advanced

8.0/10

Years Exp

SQL Advanced

7.5/10

Years Exp

ETL Pipelines Advanced

7.5/10

Years Exp

PyTorch Intermediate

7.5/10

Years Exp

SHAP Intermediate

7.5/10

Years Exp

Streamlit Advanced

7.5/10

Years Exp

AWS Intermediate

7.0/10

Years Exp

Pytest Intermediate

7.0/10

Years Exp

Plotly Intermediate

7.0/10

Years Exp

Seaborn Intermediate

7.0/10

Years Exp

Matplotlib Intermediate

7.0/10

Years Exp

Docker Intermediate

7.0/10

Years Exp

MLflow Intermediate

7.0/10

Years Exp

DVC Intermediate

7.0/10

Years Exp

Git Advanced

7.0/10

Years Exp

Flask Intermediate

6.5/10

Years Exp

Selenium Intermediate

6.5/10

Years Exp

Qdrant Intermediate

6.0/10

Years Exp

Httpx Intermediate

6.0/10

Years Exp

Gemini Intermediate

5.5/10

Years Exp

Ollama Intermediate

5.5/10

Years Exp

Pydantic Intermediate

5.5/10

Years Exp

Power BI LangChain MySql

Work Experience

Data Scientist

Optimalex

Oct 2025 - Sep 2026

Insurance Claims Prediction & Analytics | Python, Scikit-learn, XGBoost, LightGBM, SHAP, Optuna. Identified that structured claims data lacked predictive signal, and hypothesized that details buried in legal documents — permanency, wrongful-death indicator, defendant count, expert-support flag — could close the gap. Extracted these via the RAG pipeline and experimentally validated the impact, cutting indemnity model MSE by ~59% (290K → 120K), with comparable gains across the other models. Performed data preprocessing, feature engineering, and model selection, evaluating models using RMSE/MAE/R² and ROC-AUC/F1-score. Applied SHAP to identify key prediction drivers and Optuna for hyperparameter tuning and improved generalization.

Data Scientist

72 Dragons

Dec 2022 - Aug 2025

Developed a real-time monitoring dashboard using Streamlit, significantly reducing manual reporting effort and improving operational visibility across teams. Automated server and social media data collection via cron-scheduled Python scripts, streamlining the data ingestion pipeline. Analyzed and visualized social media metrics to deliver actionable insights on campaign performance and content targeting, contributing to a 15% increase in engagement. Built web scrapers using httpx and Selectolax to extract target profiles for sales outreach, increasing lead volume by 25%. Designed an automated alerting system with email notifications, cutting incident response time by 40%.

Test Engineer

L&T Technology Services

Oct 2021 - May 2022

Automated testing of I2C, SPI, PWM, and ADC peripherals using Python and Pytest, improving test coverage and reducing manual effort. Designed and executed test cases based on Jira user stories; performed both manual and automated validation to ensure feature quality. Collaborated with cross-functional teams in an Agile Scrum environment, using Git/GitHub for version control and continuous integration. Gained hands-on experience with Selenium for web test automation, enhancing end-to-end testing capabilities.