Sr. Python Developer AI/ML

Sr. Python Developer with AI/ML

Name: Navya Reddy Thadisana

Mail Id: ***********@*****.***

Contact No: 704-***-****

LinkedIn: www.linkedin.com/in/navya-reddy-t-03029884

Professional Summary:

Senior Python Developer / AI/ML Engineer with 10+ years of professional experience delivering Python applications, machine learning solutions, REST services, data-processing workflows, and cloud-based enterprise applications across healthcare, financial services, engineering, and technology environments.

Strong hands-on experience with Python development using FastAPI, Flask, and Django, building backend services, APIs, data-processing modules, application integrations, and production support components.

Recent experience at Cardinal Health focused on Generative AI, LLMs, RAG, NLP, and AI Agents, integrating intelligent capabilities with enterprise healthcare workflows and internal business applications.

Developed RAG solutions using LangChain, LangGraph, embeddings, document chunking, metadata processing, vector search, and retrieval workflows for working with internal enterprise content.

Built and integrated LLM applications using OpenAI APIs, GPT-4, Hugging Face Transformers, and AWS Bedrock, handling prompts, context preparation, response validation, and application integration.

Worked on Machine Learning solutions using Scikit-learn, PyTorch, and TensorFlow, covering data preparation, feature engineering, model training, validation, inference, and production integration.

Hands-on experience developing NLP applications for document classification, entity extraction, text normalization, semantic search, summarization, and information extraction from structured and unstructured business content.

Built production APIs with FastAPI and Flask to expose machine learning models, LLM functionality, document-processing services, and business operations to internal applications.

Developed earlier Python applications using Django, Flask, PostgreSQL, MySQL, and SQLAlchemy, implementing business logic, database operations, integrations, validation, and application enhancements.

Experienced in developing web application components using React.js, JavaScript, HTML, and CSS and integrating front-end workflows with Python-based REST APIs.

Strong experience with Pandas, NumPy, SQL, and Python-based data-processing workflows for cleansing, transformation, feature preparation, validation, reconciliation, and analytical applications.

Worked with AWS services including S3, EC2, Lambda, ECS, CloudWatch, and Bedrock to deploy, support, monitor, and integrate Python and AI/ML workloads.

Applied practical MLOps practices covering model validation, experiment management, model versioning, deployment workflows, monitoring, logging, and controlled movement of machine learning solutions across environments.

Experienced with Docker, Kubernetes, Jenkins, Git, and CI/CD processes for application builds, automated testing, containerized deployments, source-code management, and production releases.

Comfortable working with Business Analysts, product owners, data engineers, QA teams, architects, and application developers to understand requirements, troubleshoot production issues, review technical changes, and deliver maintainable solutions through Agile/Scrum practices.

Technical Skills:

Programming Languages

Python, SQL, JavaScript

AI / Generative AI

Generative AI, LLMs, GPT-4, OpenAI APIs, AWS Bedrock, Prompt Engineering, AI Agents

Machine Learning

Scikit-learn, PyTorch, TensorFlow, Classification, Regression, Anomaly Detection, Predictive Modeling, Feature Engineering, Model Validation, Model Inference

NLP

NLP, Text Classification, Entity Extraction, Text Normalization, Semantic Search, Summarization, Information Extraction, Transformers

RAG / LLM Frameworks

RAG, LangChain, LangGraph, Embeddings, Document Chunking, Metadata Enrichment, Retrieval Workflows, Vector Search

AI / ML Engineering

MLOps, Model Versioning, Model Evaluation, Experiment Tracking, Monitoring, Validation Workflows

Python Frameworks

FastAPI, Flask, Django, Django ORM, SQLAlchemy

Data Processing

Pandas, NumPy, Python Data Processing, Data Cleansing, Data Transformation, Data Validation

Frontend / Full Stack

React.js, JavaScript, HTML5, CSS3, REST API Integration, JSON

API Development

REST APIs, FastAPI Services, Flask APIs, API Validation, Authentication, Authorization, JSON/XML Integration

Databases

PostgreSQL, MySQL, SQL, SQLAlchemy, Django ORM, FAISS, Vector Databases

Cloud – AWS

AWS, Amazon S3, Amazon EC2, AWS Lambda, Amazon ECS, Amazon CloudWatch, AWS Bedrock

Containers / Deployment

Docker, Kubernetes, Containerized Python Services, Application Deployment

CI/CD & DevOps

Jenkins, Git, CI/CD, Build Automation, Automated Testing, Deployment Pipelines

Testing

PyTest, unittest, Unit Testing, Integration Testing, API Testing

Security

OAuth 2.0, JWT, Role-Based Access Control, API Authentication, Input Validation

Development Tools

PyCharm, Git, JIRA, Linux

Development Practices

Agile/Scrum, Code Reviews, Design Reviews, Defect Resolution, Production Support, Technical Documentation

Professional Experience:

Client: Cardinal Health - Dublin, OH. Feb 2026 – Till Date

Role: Sr. Python Developer with AI/ML

Responsibilities:

Led development of enterprise AI/ML solutions in Python for healthcare operations, combining Generative AI, NLP, machine learning, and LLM capabilities with existing business applications and data workflows.

Designed and implemented RAG pipelines using LangChain, LangGraph, document ingestion, chunking, metadata enrichment, embeddings, and vector databases to support contextual retrieval from internal healthcare and operational content.

Built production-ready LLM applications using GPT-4, OpenAI APIs, and Hugging Face Transformers, handling prompt construction, context management, response validation, and integration with enterprise services.

Developed AI Agents and multi-step workflows with LangGraph, enabling controlled task execution, tool invocation, routing, retrieval, and human review for operational use cases.

Applied NLP techniques for document classification, entity extraction, text normalization, semantic search, summarization, and information extraction from healthcare-related documents and unstructured business content.

Developed and fine-tuned machine learning models using PyTorch, TensorFlow, and Scikit-learn for classification, prediction, text processing, and operational analytics requirements.

Worked extensively with Transformers and Hugging Face models, evaluating pretrained models and adapting them for domain-specific language-processing and retrieval requirements.

Designed evaluation workflows for LLM and RAG applications, validating retrieval quality, response relevance, grounding, hallucination behavior, prompt performance, and regression results before production releases.

Implemented MLOps practices for model and application lifecycle management, including experiment tracking, model versioning, validation, deployment pipelines, monitoring, and controlled promotion across environments.

Built reusable Python components for data preparation, model inference, document processing, embedding generation, retrieval services, and AI workflow orchestration using PyCharm and standard Python development practices.

Developed FastAPI services to expose ML inference, document processing, retrieval, and LLM functionality through secure REST APIs consumed by enterprise applications.

Integrated AI services with existing web applications and backend workflows using Python, REST APIs, JSON, asynchronous processing, and service-level validation.

Implemented document ingestion pipelines that processed structured and unstructured data, prepared content for embedding, and maintained document metadata required for reliable RAG retrieval.

Worked with vector databases to manage embeddings, similarity search, metadata filtering, indexing, and retrieval strategies for enterprise knowledge applications.

Developed prompt templates and reusable orchestration components with LangChain, separating retrieval, generation, validation, and business rules to make LLM workflows easier to maintain and troubleshoot.

Implemented secure access patterns around OpenAI APIs and enterprise AI services, including credential management, API controls, input validation, logging, and protection of sensitive business and healthcare information.

Built data-processing and feature-engineering workflows with Python, Pandas, NumPy, and Scikit-learn to prepare datasets for model training, evaluation, inference, and analytical applications.

Supported deployment of AI/ML workloads in cloud environments using AWS services and containerized application patterns, coordinating application configuration, deployment automation, and runtime troubleshooting.

Containerized Python and AI services using Docker and integrated deployment workflows with CI/CD pipelines to move tested changes across development, QA, and production environments.

Implemented application logging, model monitoring, exception handling, and operational diagnostics for Python and LLM services, investigating failed requests, retrieval issues, model responses, and deployment problems.

Collaborated with data engineers, product owners, business analysts, and application teams to translate healthcare and operational requirements into AI/ML solutions and production-ready technical implementations.

Reviewed model and LLM outputs with business stakeholders, incorporated feedback into retrieval strategies, prompts, validation rules, and application workflows, and supported iterative releases.

Provided technical guidance to developers on Python, PyTorch, TensorFlow, LangChain, LangGraph, RAG, LLMs, NLP, MLOps, and Generative AI, while participating in design reviews, code reviews, and production issue resolution.

Environment: Python, PyTorch, TensorFlow, Scikit-learn, Pandas, NumPy, PyCharm, FastAPI, REST APIs, Generative AI, LLMs, GPT-4, OpenAI APIs, Hugging Face, Transformers, NLP, RAG, LangChain, LangGraph, AI Agents, Vector Databases, Embeddings, Prompt Engineering, MLOps, Docker, AWS, CI/CD, Git, JSON, Linux

Client: MassMutual - New York, NY. Jan 2025 – Nov 2025

Role: Python Developer with AI/ML

Responsibilities:

Designed and developed production-grade Python services supporting AI/ML, data processing, and business workflow applications within financial-services environments.

Built machine learning pipelines using Python, Pandas, NumPy, and scikit-learn for data preparation, feature engineering, model training, validation, and inference.

Developed NLP solutions for extracting, classifying, and analyzing information from policy, customer, and operational documents.

Implemented LLM-based capabilities for document summarization, information extraction, question answering, and internal knowledge-assistance workflows.

Designed RAG pipelines using LangChain, document loaders, embedding models, vector search, and retrieval workflows to provide grounded responses from enterprise content.

Developed reusable prompt engineering patterns and evaluation workflows to improve response consistency, relevance, and handling of domain-specific financial terminology.

Integrated Hugging Face models and PyTorch components for experimentation and deployment of NLP and machine-learning use cases.

Built data ingestion and transformation workflows using Python, SQL, and cloud storage services to prepare structured and unstructured data for downstream ML processing.

Developed model-serving and inference APIs using FastAPI, exposing machine-learning and LLM capabilities to internal applications and business services.

Implemented asynchronous processing and background workflows in Python for document ingestion, model inference, data enrichment, and downstream processing.

Developed React.js interfaces for internal users to submit documents, review extracted information, interact with AI-assisted workflows, and monitor processing results.

Integrated front-end applications with FastAPI and REST services using secure request handling, validation, exception management, and structured API responses.

Deployed Python and AI/ML services on AWS, using S3, Lambda, ECS, CloudWatch, and related services for application hosting, storage, monitoring, and operational support.

Used AWS Bedrock for integrating enterprise foundation models into LLM workflows while maintaining application-level controls around prompts, context, and response handling.

Implemented vector-based retrieval using technologies such as FAISS and managed vector-search services to support semantic document retrieval for RAG applications.

Developed model evaluation and validation workflows using representative business datasets, test cases, and quality checks before promoting ML and LLM components into production.

Applied SQL and PostgreSQL for transactional data access, analytical queries, data validation, and persistence requirements across Python services.

Secured application and API integrations using OAuth 2.0, JWT, role-based access controls, and enterprise authentication patterns appropriate for financial-services applications.

Containerized Python services using Docker and supported deployment through Kubernetes and CI/CD pipelines using Jenkins and Git.

Implemented application logging, error handling, monitoring, and operational diagnostics using Python logging, AWS CloudWatch, and centralized application monitoring practices.

Worked closely with business analysts, data teams, QA engineers, and architects to translate financial-services requirements into maintainable AI/ML, Python, and cloud-based solutions while supporting production releases and issue resolution.

Environment: Python, FastAPI, Django, Pandas, NumPy, scikit-learn, PyTorch, Hugging Face, NLP, Machine Learning, LLM, Generative AI, RAG, LangChain, Prompt Engineering, FAISS, AWS Bedrock, AWS S3, AWS Lambda, AWS ECS, AWS CloudWatch, React.js, JavaScript, REST APIs, SQL, PostgreSQL, Docker, Kubernetes, Jenkins, Git, OAuth 2.0, JWT, Linux.

Client: Bosch – Bengaluru, India. Apr 2021 - Jul 2024

Role: ML Engineer

Responsibilities:

Developed Machine Learning models in Python for classification, regression, anomaly detection, and predictive analytics based on Bosch engineering and operational datasets.

Built data preparation workflows using Pandas, NumPy, and SQL to clean source data, handle missing values, transform features, and prepare datasets for model training and validation.

Performed exploratory data analysis using Pandas, Matplotlib, and Seaborn to identify data patterns, outliers, feature relationships, and issues affecting model performance.

Designed and implemented feature engineering pipelines using domain-specific attributes, historical records, aggregated measurements, and derived variables to improve the quality of machine learning inputs.

Trained and evaluated models using Scikit-learn, applying algorithms such as Random Forest, Gradient Boosting, Logistic Regression, and other supervised learning techniques based on project requirements.

Developed model validation routines using cross-validation, confusion matrices, precision, recall, F1-score, ROC-AUC, and other appropriate evaluation measures before promoting models to application environments.

Built reusable Python modules for data processing, model inference, validation, logging, configuration management, and integration with downstream enterprise applications.

Developed backend services using FastAPI and Flask to expose prediction, scoring, data retrieval, and model inference functionality through secure REST APIs.

Integrated REST APIs with web-based application components, supporting user workflows for submitting input data, retrieving predictions, reviewing results, and accessing operational information.

Developed application-side functionality using React.js, JavaScript, HTML, and CSS to build dashboards and screens for displaying model outputs, validation results, and business data.

Implemented SQL queries and database integration using PostgreSQL and relational data sources for storing application records, model results, configuration details, and audit information.

Containerized Python services using Docker and prepared deployment configurations for running machine learning APIs and supporting application services consistently across development, test, and production environments.

Worked with AWS cloud services to deploy and support Python applications, APIs, data processing components, and machine learning workloads in enterprise environments.

Configured cloud-based storage and application resources using services such as Amazon S3, EC2, and CloudWatch for data storage, application hosting, logging, and operational monitoring.

Implemented API security and application controls using authentication, authorization, environment-based configuration, input validation, and controlled access to machine learning services.

Created automated unit and integration tests using PyTest for Python services, data-processing modules, REST endpoints, and model inference components before production releases.

Used Git and Jenkins to manage source code, perform build activities, execute automated tests, and support CI/CD deployments for Python and application components.

Investigated production issues involving data quality, API failures, model predictions, database connectivity, and application performance, coordinating fixes with data, application, and infrastructure teams.

Participated in requirements discussions, technical design reviews, code reviews, sprint planning, defect resolution, and production releases while working closely with business analysts, data teams, developers, and QA teams.

Environment: Python, FastAPI, Flask, Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn, SQL, PostgreSQL, REST APIs, React.js, JavaScript, HTML5, CSS3, Machine Learning, Feature Engineering, Predictive Modeling, Model Validation, Docker, AWS, Amazon S3, Amazon EC2, Amazon CloudWatch, Git, Jenkins, PyTest, CI/CD, Linux.

Client: Nagarro – Bengaluru, India. Apr 2018 – Mar 2021

Role: Python Developer

Responsibilities:

Built and consumed REST APIs for integration between internal applications and external business services.

Developed and maintained backend applications using Python, Django, and Flask based on functional and technical requirements.

Designed reusable Python modules and application components to support new features and ongoing product enhancements.

Implemented business logic, request validation, exception handling, and response processing across backend services.

Worked with PostgreSQL and MySQL for database design, queries, stored procedures, and application-level data access.

Used SQLAlchemy and Django ORM for database interactions and optimized queries used by application workflows.

Developed data processing scripts in Python for file validation, transformation, reconciliation, and scheduled operational activities.

Integrated third-party and internal services through REST APIs, handling authentication, request mapping, and response validation.

Implemented application logging and error-handling mechanisms to help troubleshoot issues across development, testing, and production environments.

Created unit and integration tests using PyTest and unittest to validate application functionality and API behavior.

Used Git for source control and followed branch, merge, and code-review practices across development activities.

Worked with Jenkins to automate application builds, test execution, and deployment activities across project environments.

Supported application deployment on AWS services and worked with development and QA teams during environment validation.

Investigated production and UAT defects, analyzed application logs and database records, and implemented fixes based on root-cause findings.

Collaborated with business analysts and QA teams to understand requirements, clarify acceptance criteria, and deliver backend changes within sprint timelines.

Participated in Agile/Scrum ceremonies including sprint planning, backlog discussions, daily stand-ups, and defect triage.

Prepared technical documentation for APIs, database changes, application workflows, deployment procedures, and production support activities.

Environment: Python, Django, Flask, REST API, PostgreSQL, MySQL, SQLAlchemy, Django ORM, PyTest, unittest, Git, Jenkins, AWS, JSON, Linux, Agile/Scrum, JIRA

Client: Mu Sigma - Bengaluru, India. Jul 2015 – Mar 2018

Role: Software Developer

Responsibilities:

Created reusable Python functions for data cleansing, transformation, and preparation before downstream analysis.

Developed and maintained Python scripts for data processing, file handling, validation, and routine application tasks.

Built application modules using Python and Django to support internal business and analytics workflows.

Worked with Pandas and NumPy to process structured datasets and perform basic data manipulation.

Wrote SQL queries to retrieve, filter, join, and validate data from MySQL and PostgreSQL databases.

Developed scripts to load data from CSV, Excel, and database sources into application workflows.

Added input validation and exception handling to Python programs to reduce failures during scheduled data processing.

Investigated data discrepancies by tracing records through Python scripts and database queries and worked with analysts to resolve issues.

Built simple REST API endpoints using Django to exchange data between internal application components.

Assisted in developing scheduled Python jobs for recurring data extraction, transformation, and report preparation activities.

Used Git for source-code management, branching, code updates, and maintaining project versions.

Performed unit testing and debugging of Python modules using PyTest and built-in Python testing practices.

Reviewed existing code, fixed defects, and made enhancements based on functional requirements provided by business and analytics teams.

Worked with JSON, XML, and other structured data formats while integrating application components and external data sources.

Prepared technical documentation for Python modules, database queries, configuration details, and application support procedures.

Supported application releases by validating changes in development and test environments and coordinating defect fixes with senior developers.

Environment: Python, Django, Pandas, NumPy, SQL, MySQL, PostgreSQL, REST API, JSON, XML, PyTest, Git, Linux, CSV, Excel.

Contact this candidate