Building production-ready ML systems that turn messy data into reliable decisions.
Machine Learning Engineer with 4+ years of experience building data-driven and production-ready systems using Python and SQL. Strong in feature engineering, model evaluation, and scalable training/inference pipelines.
About
Quick Info
Machine Learning & Data Engineer @ CPAC (5M+ records, dashboards, pipelines, monitoring)
Microsoft Certified: Fabric Data Engineer Associate
Avila University (M.S. Business Analytics), Rowan University (M.S. Computer Science), Osmania University (B.S. Computer Science)
Experience
Partnered with stakeholders to frame ML problems; built Python pipelines for feature extraction/validation from 5M+ records; developed predictive models for forecasting & optimization; implemented monitoring checks to detect drift; optimized SQL/Python processing to reduce latency and manual work by 40%; delivered dashboards for technical/non-technical audiences.
Designed, trained, and deployed ML models for segmentation, forecasting, and risk scoring; owned full ML lifecycle; built training/inference pipelines on 2M+ records; developed APIs/services for downstream apps; added validation, monitoring, and logging to improve reliability; automated workflows to reduce recurring issues by 30%.
Built forecasting and analytics systems; automated reporting using Python (50% less manual effort); maintained feature pipelines; supported interfaces and validated data exchanges; created executive dashboards to standardize performance reporting.
Projects
Collection of daily AI and machine learning experiments focusing on agent-based reasoning, automation logic, prompt-driven workflows, and applied Python implementations. Emphasizes rapid prototyping and iterative experimentation.
Implemented a Deep Deterministic Policy Gradient (DDPG) algorithm for continuous action-space environments. Covers actor–critic architecture, experience replay, target networks, and training stability techniques.
Built a supervised machine learning pipeline to predict medical risk outcomes using structured healthcare data. Includes preprocessing, feature engineering, model training, evaluation metrics, and result interpretation.
Blogs (LinkedIn)
How generative AI can support data-driven decision making in social service and community planning organizations.
A practical walkthrough of applying generative AI tools to design, evaluate, and inform real-world social impact initiatives.
An overview of how generative AI is reshaping data science, analytics, and machine learning roles.
Skills
Feature engineering • Model training • Evaluation metrics • Forecasting • Segmentation • Risk scoring • Batch & near-real-time pipelines • Data validation • Monitoring & drift checks
Python • SQL • Power BI • Advanced Excel • Git • Databricks • Snowflake • ELK Stack