AI/ML Engineer

Betha Shanmukha Satyadev

AI/ML Python Engineer Full Stack Developer Overland Park, KS 66223 ****************@*****.*** 913-***-****

Professional Summary

Results-driven AI/ML Python Engineer with 3+ years of experience designing and deploying end-to-end data-driven applications, from predictive model development to full-stack user interfaces. Proficient in Machine Learning, Statistical Modeling, and Natural Language Processing (NLP). Skilled in building scalable ETL pipelines, data warehouses, and real-time reporting systems using Python, Spark, Hadoop, SQL, and AWS Cloud. Adept at developing comprehensive solutions involving data ingestion, feature engineering, model training, validation, and deployment. Strong expertise in data visualization with Tableau and full-stack development using Flask/Django, Angular, HTML, and CSS. Well-versed in Agile methodologies to deliver robust, scalable, and cost-effective solutions.

Technical Skills

Languages: Python, SQL, Bash, HTML5, CSS3, JavaScript

ML/AI: scikit-learn, TensorFlow, Keras, XGBoost, PyTorch (basics), Bayesian HMM, Caffe Deep Learning

Full-Stack Development: Flask, Django, REST APIs, Angular (basics), jQuery

Data Engineering: PySpark, Pandas, NumPy, Spark SQL, ETL, HDFS, Hadoop Ecosystem (Hive, Sqoop, Pig, Oozie, Flume)

Cloud Platforms: AWS (EC2, S3, RDS, IAM, Route 53, VPC)

Databases: MySQL, PostgreSQL, NoSQL, Teradata, Oracle 10g/11g, SQL Server

BI/Visualization: Tableau, Power BI, Business Objects, Matplotlib, Seaborn, Plotly

DevOps/Tools: Git, Jenkins, Docker, Jupyter, Jira, Informatica, ER Studio

OS/IDEs: Linux, Windows, PyCharm, Jupyter Notebook, VS Code

Professional Experience

AI/ML Python Engineer UnitedHealth Group (UHG), Atlanta, GA August 2024 – June 2025

Engineered and deployed machine learning classification models that improved fraud detection accuracy by 15%, leading to $500K+ in annual cost savings.

Developed secure RESTful APIs using Flask to serve real-time predictions, integrating backend models with front-end applications.

Built interactive front-end user interfaces using Angular, HTML, and CSS to visualize model predictions and enable data input for real-time analysis.

Designed scalable data pipelines in AWS and automated ETL workflows with PySpark, Pandas, and Spark SQL, reducing data processing time by 40%.

Implemented NLP models to extract insights from patient/provider records, streamlining claims validation processes.

Automated model retraining pipelines in AWS Cloud using Python scripts, ensuring real-time updates with new incoming healthcare datasets.

Pioneered a data validation framework across enterprise-wide healthcare projects, ensuring data integrity and quality.

Utilized Teradata utilities for large-scale data migrations, improving reporting system efficiency.

Collaborated with senior leadership to translate business questions into data-driven solutions, designing Tableau dashboards for critical healthcare KPIs.

Operated within Agile methodologies, reducing project delivery time by 20% and ensuring alignment with stakeholder requirements.

Python Developer HCL Technologies, Chennai, India February 2021 – September 2023

Built and deployed machine learning models for customer churn and fraud detection, reducing potential financial losses by 10%.

Developed and maintained REST APIs using Django to facilitate seamless communication between front-end applications and ML models.

Created dynamic dashboards using HTML, CSS, and jQuery to display model performance metrics and provide intuitive user interfaces.

Managed the end-to-end model lifecycle, including data collection, cleaning, transformation, feature engineering, validation, and gap analysis.

Streamlined ETL processes with Teradata utilities, improving data accessibility for business intelligence teams.

Implemented NLP-based classification and text mining workflows (NLTK, scikit-learn) to categorize unstructured client text, improving content management efficiency.

Delivered OLAP cubes, dashboards, and scorecards using Tableau, Business Objects, and Power BI, providing real-time insights that enabled data-driven decision-making.

Developed Python scripts in AWS Cloud to automate data ingestion and classification pipelines, significantly improving the speed of dynamic response labeling.

Projects

Customer Churn Prediction Dashboard

Full-Stack Application: Developed an end-to-end web application for predicting and visualizing customer churn.

Backend (Flask): Built a machine learning model (XGBoost) deployed via a Flask API to provide churn probabilities.

Frontend (HTML, CSS, JavaScript): Designed an interactive dashboard to visualize churn risk, key contributing factors, and provide a user interface for data input.

Healthcare Claim Classifier

AI/ML Solution: Created an automated system for classifying healthcare claims using Natural Language Processing.

Model Development: Implemented a text classification model using scikit-learn and NLTK to categorize claims based on unstructured text data.

Deployment (Docker, AWS): Containerized the model using Docker and deployed it on an AWS EC2 instance, making it accessible via a REST API for integration with other systems.

Education

Master of Science in Computer Science

oUniversity of Central Missouri, MO — GPA: 3.5

Bachelor of Engineering in Computer Science & Engineering

oSathyabama Institute of Science and Technology, Chennai, India — GPA: 8.8 / 10

Contact this candidate