Deepthi - Python AI/ML Developer

Deepthi

Python Developer - AI/ML

**********@*****.*** 408-***-****

PROFESSIONAL SUMMARY:

Python Developer with 8+ years of experience building backend, data-driven, and AI-enabled applications across enterprise and cloud environments. Skilled in Python 3.x, RESTful API development (Flask, Django, FastAPI), and microservices architectures for scalable systems. Experienced in machine learning, deep learning, and NLP, including feature engineering, model development, and evaluation using Scikit-learn, PyTorch, and TensorFlow. Hands-on with large language models and Hugging Face frameworks for NLP projects. Proficient in data engineering using Pandas, NumPy, SQL, MySQL, PostgreSQL, MongoDB, and FAISS for efficient pipelines and vector search applications. Familiar with deploying cloud-based solutions on AWS (EC2, S3, SageMaker, RDS), containerized applications with Docker, and CI/CD pipelines using Jenkins. Understands MLOps and DevOps practices, including experiment tracking, versioning, deployment, and monitoring, supporting reliable production ML systems. Effective communicator and collaborator, experienced in Agile/Scrum environments.

TECHNICAL SKILLS:

Programming, Web & Scripting: Python (3.x), SQL, JavaScript, HTML5, CSS3

Machine Learning & AI: Model development, feature engineering, data preprocessing, regression, classification, clustering, evaluation (F1-score, RMSE), predictive analytics, NLP for text classification and semantic analysis, LLMs (Hugging Face Transformers/APIs), PyTorch, TensorFlow.

Data Engineering, Analytics & Visualization: Exploratory Data Analysis (EDA), Data Cleaning, Statistical Analysis, Pandas, NumPy, Jupyter Notebook, Data Visualization, Matplotlib, Plotly, Relational Database Design, NoSQL Data Modeling, FAISS (Vector Database)

Backend, APIs & Distributed Systems: Flask, Django, Django REST Framework (DRF), FastAPI, RESTful API Development, Microservices Architecture, SQLAlchemy, Django ORM, Celery, Redis, Background Job Processing, Message Queues

Databases & Cloud Platforms:

MySQL, PostgreSQL, MongoDB, AWS RDS, AWS EC2, AWS S3, AWS SageMaker, AWS IAM

MLOps, DevOps & CI/CD: MLflow, Model Versioning, Experiment Tracking, Model Serialization, Joblib, Pickle, End-to-End ML Pipelines, MLOps Best Practices, Automated Deployment, Docker, Jenkins, CI/CD Pipelines

Monitoring, Security & Quality: Application Monitoring, Model Monitoring, Logging Frameworks, Error Handling, Metrics Collection, Production Incident Management, Root Cause Analysis, OAuth 2.0, Secure API Authentication, Authorization, Access Control, Pytest, Unit Testing, Integration Testing, Automated Testing

Tools, Platforms & Collaboration: Linux, Apache, Git, Code Reviews, Branching Strategies, Agile, Scrum, Jira, Confluence, Technical Documentation

CERTIFICATION:

PCAP™ - Certified Associate Python Programmer (PCAP-31-03)

EXPERIENCE:

Rabun County Bank, Clayton, GA

Sr. Python Developer – AI/ML May 2024 to Present

Contributed to Python-based AI/ML applications for predictive analytics and workflow automation, supporting business stakeholders across enterprise teams.

Performed feature engineering, data preprocessing, and data normalization to improve model robustness and consistency across training and inference datasets.

Designed scalable data pipelines leveraging MySQL, handling efficient data extraction and data transformation for AI and ML workflows.

Developed and optimized machine learning models using Scikit-learn, focusing on model optimization techniques to improve accuracy, performance, and scalability.

Assisted in developing NLP applications using LLMs and Hugging Face frameworks, applying prompt engineering for selected text classification tasks.

Built and trained deep learning solutions using PyTorch, supporting advanced analytics and production-grade AI workloads.

Deployed and managed cloud AI workloads on AWS EC2, AWS S3, and AWS SageMaker, supporting secure, scalable model hosting and training environments.

Assisted in enhancing logging and monitoring processes, improving visibility into system errors, and supporting faster issue resolution.

Containerized applications using Docker provide consistent environments across development, testing, and deployment.

Implemented natural language processing (NLP) pipelines for text classification and semantic analysis, enabling intelligent text understanding and contextual insights.

Implemented vector embeddings using FAISS to enable high-performance semantic search and similarity-based retrieval systems.

Developed FastAPI endpoints for real-time and batch ML inference, collaborating with the backend team to integrate models into existing systems.

Implemented model serialization using Joblib, ensuring reliable artifact storage, portability, and reuse across environments.

Managed model versioning and experiment tracking using MLflow, supporting reproducibility, auditability, and ML governance standards.

Established end-to-end ML pipelines aligned with MLOps best practices, integrating automated testing, deployment, and monitoring.

Supported model monitoring and drift detection for production ML services, helping identify performance issues and enabling periodic retraining where necessary.

Collaborated within Agile and Scrum teams, contributing to sprint planning, delivery timelines, and comprehensive technical documentation for AI/ML systems.

Managed source code using Git and version control, participating in structured code reviews to ensure clean, maintainable, and secure codebases.

BEKHealth, Raleigh, NC

Python Developer October 2022 to April 2024

Designed and developed scalable RESTful APIs using Python, Django REST Framework (DRF), and FastAPI to support data-driven and machine learning–powered applications.

Built robust data access layers using Django ORM, working with PostgreSQL and MongoDB to support efficient data modeling for analytical and transactional workloads.

Developed ML models in Scikit-learn for regression, classification, and clustering tasks, supporting predictive use cases in healthcare analytics.

Conducted thorough model evaluation using industry-standard accuracy metrics, including F1-score and RMSE, to ensure reliable and unbiased results.

Built deep learning models using TensorFlow to support advanced predictive analytics and complex pattern recognition tasks.

Serialized trained models using Pickle, managing model serialization and model versioning to support reproducibility and controlled deployments.

Designed and executed end-to-end ETL pipelines, handling large-scale data processing and data transformation to prepare datasets for analytics and machine learning.

Conducted data cleaning, feature engineering, and EDA in Pandas and NumPy to support model training and analytics workflows.

Packaged data science applications with Docker for consistency across development and testing environments, collaborating with DevOps for production deployment.

Deployed machine learning models on AWS EC2, AWS S3, and AWS SageMaker, delivering scalable cloud-based ML solutions for real-world production use.

Managed source code using Git and version control, participating in structured code reviews to maintain high-quality, maintainable analytics workflows.

Collaborated within Agile and Scrum teams, contributing to sprint planning, iterative development, and continuous improvement of analytics workflows.

Implemented end-to-end model deployment, including model monitoring, model retraining, and model drift detection to maintain long-term model accuracy and reliability.

Created interactive and static data visualizations using Matplotlib and Plotly to communicate insights effectively to technical and non-technical stakeholders.

Conducted experimentation and analysis using Jupyter Notebook, maintaining detailed experiment documentation to support traceability and knowledge sharing.

Bridge City Insurance, Portland, OR

Python Developer June 2020 to September 2022

Developed and maintained scalable backend development solutions using Python 3.x and Flask, delivering high-performance services aligned with modern application requirements.

Deployed and supported applications on AWS EC2 and AWS S3, managing cloud infrastructure components with secure access control using AWS IAM.

Designed and implemented RESTful APIs following microservices architecture, enabling modular, loosely coupled services for improved scalability and maintainability.

Built and managed relational and NoSQL data stores using MySQL, MongoDB, and AWS RDS, applying effective data modeling and schema design strategies.

Utilized SQLAlchemy and ORM frameworks to streamline database interactions, improve query efficiency, and maintain clean separation between business logic and data layers.

Worked with Celery and Redis to manage background tasks and asynchronous processes for selected backend services.

Containerized applications using Docker and containerization best practices, ensuring consistent environments across development, testing, and production.

Assisted in monitoring and logging for backend applications to help identify performance issues and support system reliability.

Conducted debugging, root-cause analysis, and production support activities on Linux environments to resolve incidents and maintain service uptime.

Designed and maintained CI/CD pipelines using Jenkins, enabling build automation, deployment automation, and faster release cycles with minimal downtime.

Supported secure authentication and authorization using OAuth 2.0 for select services, ensuring compliance with basic security standards.

Collaborated within Agile and Scrum teams, actively participating in sprint planning, daily stand-ups, and retrospectives using Jira and Confluence for tracking and documentation.

Wrote and maintained comprehensive unit testing and integration testing suites using Pytest, improving code coverage and preventing regression issues.

AppLovin, Palo Alto, CA

Python Developer March 2017 to May 2020

Contributed to Python/Django web applications, focusing on reusable components and maintainable code to support long-term application growth.

Designed and optimized relational databases using PostgreSQL and SQL, performing database design, query optimization, and indexing to improve application performance and reliability.

Deployed and maintained applications on AWS EC2 and AWS S3, supporting cloud computing initiatives and ensuring high availability, scalability, and secure data storage.

Worked with RESTful APIs to enable data exchange between front-end and back-end systems, supporting secure integrations for multiple services.

Developed responsive user interfaces using HTML5, CSS3, JavaScript, Bootstrap, and jQuery, ensuring cross-browser compatibility and consistent behavior across modern web browsers.

Implemented responsive web design principles to optimize applications for desktop, tablet, and mobile devices, improving user experience and accessibility.

Configured and managed application environments on Linux servers using Apache, handling application deployment, server tuning, and production issue resolution.

Managed source code using Git, following structured version control, branching strategies, and conducting peer code reviews to maintain code quality and collaboration standards.

Performed unit testing, debugging, and root-cause analysis to identify defects early in the development lifecycle and ensure stable, production-ready releases.

EDUCATION:

Master of Computer Application - Nagarjuna University, India

Contact this candidate