Machine Learning Engineer

Dhana Laxmi Boddula

Phone: +1-469-***-**** Email: ******************@*****.***

LinkedIn: https://www.linkedin.com/in/boddula-dhana-laxmi-5b7b13228/

Professional Summary

Results-oriented Python and Machine Learning Engineer with 2+ years of hands-on experience in developing scalable APIs, deploying cloud-based applications, and integrating deep learning and NLP systems. Strong foundation in backend development, REST API architecture, and real-time communication using WebSockets. Proficient in Django, TensorFlow, and AWS, with a proven track record of delivering end-to-end solutions in both startup and enterprise environments. Passionate about writing clean code, collaborating with diverse teams, and building robust, production-ready systems that align with business needs.

Skills

Languages: Python, SQL, JavaScript, HTML, CSS

Frameworks & Tools: Django, Django REST Framework, Flask, FastAPI, Celery, Git

Libraries: TensorFlow, Scikit-learn, Pandas, NumPy, Matplotlib, OpenCV, Coqui TTS

Cloud & Deployment: AWS EC2, Nginx, Gunicorn, Docker

Database: PostgreSQL, MySQL, SQLite

Concepts: REST APIs, TTS, Websockets, IoT Integration, Multithreading

ML Techniques: Deep Learning, NLP, Voice Synthesis, Classification, Transfer Learning

Soft Skills: Collaboration, Agile, Communication, Documentation

Projects

Counterfeit Currency Detection

Built a counterfeit detection model using the Xception CNN architecture for classifying currency notes.

Incorporated image preprocessing steps like edge detection, watermark analysis, and segmentation.

Trained and validated the model using TensorFlow and Pandas, with CSV-based batch inputs.

Achieved accuracy improvements over legacy CNNs for multiple orientations and noise levels.

Evaluated model performance for robustness across watermark and orientation scenarios.

Deployed and tested the solution in Spyder IDE using real-time simulation inputs.

Documented performance metrics and analysis results for comparative studies.

Optimized the model for inference efficiency suitable for real-time deployments.

Prediction of Contaminants in Water Using Machine Learning

Developed machine learning models to classify water contamination based on physicochemical properties.

Collected and cleaned data from WHO, EPA, and Kaggle to build feature-rich datasets.

Applied Random Forest, XGBoost, and Neural Networks for classification and regression tasks.

Performed EDA and visualization using Matplotlib and Seaborn to identify key contaminants.

Used GridSearchCV for hyperparameter tuning and model optimization.

Built and deployed a Flask API to serve contamination predictions in real time.

Tracked system logs and response metrics for debugging and reliability analysis.

Delivered 92%+ accuracy on unseen data, enabling reliable decision support systems.

Professional Experience

Associate ML Engineer Amat (applied materials), Saint Louis, Missouri

Feb 2024 – Apr 2025

Built ML pipelines for healthcare claims fraud detection using CatBoost and Isolation Forest.

Preprocessed large-scale datasets using PySpark, improving efficiency and speed by 45%.

Developed FastAPI services for serving trained ML models with real-time response handling.

Implemented MLflow for experiment tracking, reproducibility, and version management.

Created dashboards with Plotly Dash to visualize fraud detection KPIs and anomalies.

Collaborated with cross-functional teams to refine model inputs based on domain feedback.

Conducted unit testing and integrated workflows with GitHub Actions for CI/CD support.

Presented model performance and updates during Agile sprints and stakeholder demos.

Python Developer Value Labs, Hyderabad, India

Jun 2022 – Aug 2023

Developed REST APIs using Django REST Framework with custom roles, sub-users, and permissions.

Used Celery for handling long-running background tasks like bulk data insertion and reports.

Implemented custom middleware, extended Django auth models, and added token authentication.

Deployed production environments using AWS EC2, Nginx, and Gunicorn.

Built real-time WebSocket communication channels for frontend updates.

Trained a voice synthesis model using Coqui and TensorFlow for generating TTS outputs.

Integrated IoT devices using MQTT for real-time logistics tracking with RFID encoding.

Built an LLM chatbot using HuggingFace to convert user queries into SQL database searches.

Education

Master of Science in Information Technology Management

St. Francis College, New York Sep 2023 – May 2025 CGPA: 3.467/4

Bachelor of Technology in Computer Science and Engineering

Guru Nanak Institutions, Hyderabad Grad: 2023 CGPA: 7.64/10

Contact this candidate