Available to hire
Hi, I’m Nagasai Nagaraju, an AI & Machine Learning Engineer with 5+ years of hands-on experience building robust ML systems. I design and shipping production-grade AI solutions focused on scalability, reliability, and impact across domains.
I specialize in Generative AI, LLM-powered solutions for chatbots, summarization, and document intelligence. I enjoy architecting end-to-end AI pipelines, MLOps, and multi-agent workflows, leveraging tools like LangChain, LangGraph, OpenAI SDK, FAISS, Pinecone, and Weaviate to deliver capable, context-aware AI at scale.
Skills
Experience Level
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Language
English
Fluent
Javanese
Advanced
Bashkir
Advanced
Work Experience
Gen AI Full Stack Developer at T-Mobile
February 1, 2025 - PresentDeveloped end-to-end Generative AI applications integrating LLMs with front-end and back-end architectures; built Retrieval-Augmented Generation (RAG) pipelines using LangChain and LlamaIndex connected to vector databases; implemented prompt engineering, including few-shot and chain-of-thought prompting, and fine-tuned Hugging Face transformers on domain datasets; created agentic AI systems using AutoGPT and CrewAI for autonomous task execution and workflow orchestration; integrated document ingestion, semantic search, and knowledge retrieval pipelines with PostgreSQL and Redis backends; developed full-stack microservices using React.js, FastAPI, and Node.js, deployed on Microsoft Azure (App Services, AKS, Functions); containerized and automated deployment with Docker, Kubernetes, and CI/CD pipelines using GitHub Actions; tracked experiments and managed model lifecycles with MLflow, Databricks, and Delta Lake; designed and consumed REST and GraphQL APIs; applied model observability and
AI Full Stack Developer at Cardinal Health
December 1, 2024 - September 5, 2025Designed and deployed end-to-end AI applications integrating machine learning models with scalable full-stack architectures; built predictive and generative AI solutions using Python (PyTorch, TensorFlow, Scikit-learn) and deployed them via FastAPI/Flask backends; implemented LLM-based features using LangChain, Hugging Face Transformers, and Azure OpenAI Service; developed front-end interfaces using React.js and Next.js; created data pipelines for ingestion, preprocessing, and model training using Databricks (Spark, MLflow, Delta Lake) and PostgreSQL; deployed cloud-native microservices on Microsoft Azure using App Services, AKS, and Functions with containerization via Docker and Kubernetes; automated CI/CD workflows with GitHub Actions and infrastructure as code using Terraform; architected RAG pipelines and semantic search using vector databases (FAISS, Pinecone); ensured reliability and scalability through unit, integration, and end-to-end testing using PyTest, Jest, and Cypress; co
Full Stack Developer at LTI MINDTREE, Hyderabad
December 1, 2022 - September 5, 2025Developed and deployed end-to-end web applications using React.js, Node.js, Express.js, and FastAPI; designed RESTful and GraphQL APIs with secure authentication, efficient data flow, and seamless integration with PostgreSQL; built responsive front-end interfaces with React.js and Next.js, implementing state management with Redux and hooks; containerized microservices using Docker and orchestrated deployments via Kubernetes on Microsoft Azure; automated CI/CD pipelines using GitHub Actions and implemented infrastructure as code with Terraform; integrated caching (Redis) and message queuing to optimize performance and reliability; implemented unit, integration, and end-to-end testing using Jest, Mocha, and Cypress; collaborated with cross-functional teams in Agile/Scrum methodologies and monitored application performance using Azure Monitor and logging tools.
Gen AI Full Stack Developer at T-Mobile
February 1, 2025 - PresentDeveloped end-to-end Generative AI applications, integrating OpenAI/Azure OpenAI with custom front-end and back-end architectures. Built RAG pipelines using LangChain and LlamaIndex and connected to FAISS; implemented prompt engineering strategies and domain-specific model finetuning on Hugging Face transformers. Created agentic AI systems with AutoGPT and CrewAI, built ingestion and semantic search pipelines with PostgreSQL/Redis, and delivered microservices with React, FastAPI, and Node.js on Azure. Established CI/CD with GitHub Actions, containerized with Docker/Kubernetes, and enabled model observability with MLflow/Delta Lake. Implemented REST/GraphQL APIs and executed robust testing using PyTest/Jest/Cypress. Worked in Agile/Scrum with Jira/Confluence.
AI Full Stack Developer at Cardinal Health
December 1, 2024 - September 5, 2025Designed and deployed AI-powered applications integrating ML models with scalable full-stack architectures. Built predictive and generative AI features using Python (PyTorch, TensorFlow) and deployed via FastAPI/Flask. Implemented LangChain and Azure OpenAI-based features, built real-time insights with React/Next.js front-ends, and orchestrated data pipelines with Databricks (Spark, MLflow, Delta Lake) and PostgreSQL. Deployed cloud-native microservices on Azure (App Services, AKS, Functions) with Docker/Kubernetes; automated CI/CD using GitHub Actions and Terraform. Architected RAG pipelines and semantic search with vector databases (FAISS, Pinecone), and ensured quality through PyTest/Jest/Cypress. Collaborated in Agile with cross-functional teams.
Full Stack Developer at LTI MINDTREE, Hyderabad
December 1, 2022 - September 5, 2025Developed end-to-end web applications using React.js, Node.js/Express.js, and FastAPI, delivering high performance and scalable architectures. Designed RESTful and GraphQL APIs with secure authentication and efficient data flows; built responsive front-ends with React/Next.js and Redux. Containerized microservices with Docker and orchestrated deployments with Kubernetes on Azure. Automated CI/CD with GitHub Actions; implemented infrastructure as code with Terraform. Integrated caching with Redis and message queuing to improve reliability; wrote unit, integration, and end-to-end tests; monitored performance with Azure Monitor. Collaborated with cross-functional teams in Agile/Scrum to deliver projects on time.
AI/ML Engineer at T-Mobile (Client engagement)
February 1, 2025 - PresentDeveloped end-to-end Generative AI applications integrating LLMs (Llama, Azure OpenAI) with custom front-end (React) and back-end (FastAPI) architectures. Leveraged Hugging Face Transformers, LangChain, and LangGraph to orchestrate retrieval, multi-step workflows, and tool integrations for production-ready solutions. Built Retrieval-Augmented Generation (RAG) pipelines using LangChain and LlamaIndex, connected to vector databases like FAISS, Pinecone, and Weaviate. Implemented prompt engineering strategies including few-shot and chain-of-thought prompting to improve LLM response quality. Fine-tuned Hugging Face transformers and open-source LLMs on domain-specific data for enterprise AI solutions. Created agentic AI systems using AutoGPT and Crew AI for autonomous task execution and workflow orchestration. Integrated document ingestion, semantic search, and knowledge-retrieval pipelines with PostgreSQL and Redis backends. Developed full-stack microservices for AI applications using Reac
AI/ML Engineer at Cardinal Health
December 31, 2024 - September 26, 2025Designed and deployed end-to-end AI applications integrating machine learning models with scalable full-stack architectures. Built predictive and generative AI solutions using Python (PyTorch, TensorFlow, Scikit-learn) and deployed via FastAPI/Flask backends. Implemented LLM-based features using LangChain, Hugging Face Transformers, and AWS Bedrock. Developed front-end interfaces with React and Next.js, integrated with AI-powered APIs for real-time insights. Created data pipelines for ingestion, preprocessing, and model training using Databricks and AWS Glue; deployed cloud-native microservices on AWS SageMaker, ECS, Lambda, and EKS with containerization via Docker and Kubernetes. Automated CI/CD pipelines with GitHub Actions and Terraform; implemented caching (Redis) and messaging to optimize performance. Architected RAG pipelines and semantic search using vector databases (FAISS, Pinecone, Weaviate) for knowledge-intensive apps. Collaborated with cross-functional teams in Agile envir
AI/ML Engineer at LTIMindtree (Hyderabad)
December 31, 2022 - September 26, 2025Full-stack developer responsibilities: Designed and deployed end-to-end web apps using React.js, Node.js, and Express.js; implemented secure RESTful APIs and efficient data flows with PostgreSQL/MySQL. Containerized microservices using Docker and orchestrated with Kubernetes in Azure cloud; automated CI/CD with GitHub Actions and Terraform. Integrated Redis caching and messaging to optimize performance; conducted unit, integration, and end-to-end testing with Jest, Mocha, and Cypress. Collaborated with cross-functional teams in Agile/Scrum to deliver production-grade AI-enabled solutions.
AI/ML Engineer at T-Mobile
February 1, 2025 - PresentDeveloped end-to-end Generative AI applications integrating LLMs with scalable front-end (React) and back-end (FastAPI) architectures. Built retrieval-augmented generation pipelines using vector databases and orchestrated AI workflows with multi-step pipelines. Implemented prompt-engineering strategies and fine-tuned open-source models; created agentic AI systems for autonomous task execution. Deployed REST/GraphQL APIs, containerized services, and automated CI/CD workflows; managed ML ops for training, deployment, monitoring, and drift detection to ensure robust production readiness.
AI/ML Engineer at Cardinal Health
December 31, 2024 - September 26, 2025Designed and deployed end-to-end AI applications integrating ML models with scalable full-stack architectures. Built predictive and generative AI solutions using Python (PyTorch, TensorFlow) and deployed via FastAPI/Flask with React front-end. Implemented LLM-based features using LangChain and Hugging Face Transformers; created real-time insights pipelines with PostgreSQL and Redis. Established automated CI/CD pipelines with GitHub Actions, Docker, and Kubernetes; containerized on cloud platforms. Implemented monitoring with Prometheus/Grafana and drift detection for production-grade AI systems; collaborated with cross-functional teams in Agile/Scrum.
Full Stack Developer at LTIMindtree
December 31, 2022 - September 26, 2025Full-stack development of web applications using React.js, Node.js, and Express.js with secure RESTful APIs and efficient data flow (PostgreSQL). Containerized microservices with Docker and orchestrated deployments on Kubernetes in AWS. Automated CI/CD workflows with GitHub Actions and Terraform. Architected RA(G) pipelines and semantic search using vector databases (FAISS, Pinecone, Weaviate). Implemented end-to-end testing with Jest and Cypress; collaborated with cross-functional teams in Agile/Scrum to deliver production-grade AI-enabled systems.
Gen AI/ML Engineer at T-Mobile
February 1, 2025 - PresentDeveloped end-to-end Generative AI applications by integrating LLMs (Llama, Azure OpenAI) with custom front-end (React) and back-end (FastAPI). Orchestrated retrieval-augmented generation (RAG) using LangChain and LangGraph, built multi-step workflows, and implemented retriever pipelines connected to vector databases like FAISS. Applied prompt engineering strategies (few-shot, chain-of-thought) to improve LLM responses. Fine-tuned Hugging Face Transformers and open-source LLMs on domain-specific data for enterprise AI. Created agentic AI systems using AutoGPT and Crew AI for autonomous task execution and workflow orchestration. Integrated document ingestion, semantic search, and knowledge-retrieval pipelines with PostgreSQL and Redis. Built full-stack microservices for AI apps using React.js, FastAPI, and Node.js, deployed on Azure (App Services, AKS, Functions). Containerized and automated deployments with Docker and Kubernetes. Built and managed MLOps pipelines on Azure using Azure M
AI/ML Engineer at Cardinal Health
December 31, 2024 - September 26, 2025Designed and deployed end-to-end AI applications by integrating machine learning models with scalable full-stack architectures. Built predictive and generative AI solutions using Python (PyTorch, TensorFlow, scikit-learn) and deployed via FastAPI/Flask backends. Implemented LLM-based features using LangChain, Hugging Face Transformers, and AWS Bedrock; developed front-end interfaces with React.js and Next.js; data pipelines using Databricks and AWS Glue; deployed cloud-native microservices on AWS SageMaker, ECS, EKS; automated CI/CD with GitHub Actions and Terraform; integrated caching (Redis) and messaging (SQS/Kafka); implemented unit/integration/end-to-end testing (Jest, Mocha, Cypress). Collaborated with cross-functional teams in Agile/Scrum to deliver production-grade AI systems.
Full Stack Developer at LTIMindtree
December 31, 2022 - September 26, 2025Developed and deployed end-to-end web applications using React.js, Node.js, Express.js; designed RESTful APIs with secure authentication; built responsive front-ends with React and Next.js; containerized microservices with Docker; orchestrated deployments via Kubernetes on Microsoft Azure; automated CI/CD pipelines; integrated Redis caching and messaging; tested with Jest and Cypress; collaborated with cross-functional teams in Agile/Scrum to deliver production-grade AI solutions.
Gen AI Engineer at T-Mobile
February 1, 2025 - PresentDesigned and deployed agentic AI systems using LangChain, LangGraph, and OpenAI API (GPT-4o) with dynamic function calling and stateful memory for autonomous task execution. Developed and launched domain-specific chatbots powered by GPT-4o and LLaMA-2, integrated with FastAPI and structured prompt templates for scalable, consistent user interaction. Built Retrieval-Augmented Generation (RAG) pipelines with Azure AI Search, FAISS, and Pinecone, enhancing contextual retrieval and improving response accuracy by 35%. Fine-tuned LLMs (LLaMA, Falcon, Mistral) using LoRA, PEFT, and advanced prompt engineering techniques. Implemented advanced prompt engineering strategies—few-shot, zero-shot, and chain-of-thought—to improve reasoning depth and reduce hallucinations across production models.
AI/ML Engineer at Cardinal Health
January 1, 2023 - December 31, 2024Engineered end-to-end AI/ML pipelines for risk scoring, churn prediction, fraud detection, telematics underwriting, and sentiment analysis using Python, PySpark, scikit-learn, and XGBoost. Built predictive and generative AI solutions with PyTorch, TensorFlow, Keras, and Hugging Face, implementing LLM-based features using LangChain and LangGraph, plus AWS Bedrock with LoRA/PEFT fine-tuning. Developed NLP and voice-bot pipelines for NER, summarization, translation, and multilingual chatbot capabilities using spaCy, BERTopic, RoBERTa/BERT, and DialogFlow. Architected RAG pipelines and semantic search with FAISS, Pinecone, Weaviate, and OpenSearch for contextual retrieval and tool-based reasoning. Delivered cloud-native microservices and APIs with FastAPI, Flask, and Spring Boot WebFlux, orchestrated on Kubernetes (AKS/EKS) and deployed on AWS SageMaker, Azure ML, and Google Cloud Vertex AI.
ML Engineer at LTI Mindtree
July 1, 2020 - December 31, 2022Built and optimized deep learning solutions for image classification, OCR, and sequence modeling in insurance and finance domains. Developed NLP pipelines for NER, sentiment analysis, and text classification with spaCy, NLTK, and Hugging Face Transformers, including a YOLO-based CV pipeline achieving 95% accuracy on exam proctoring. Executed end-to-end Azure ML projects leveraging Azure ML, Azure Functions, and Azure DevOps for scalable deployments, monitoring, and CI/CD. Created and deployed AI microservices with Flask, FastAPI, and Spring Boot WebFlux, integrated with Kafka for real-time event handling. Reusable Python/Jupyter workflows for EDA, feature engineering, hyperparameter tuning, with Pandas, NumPy, Seaborn, and Matplotlib.
AI / ML Engineer at Cardinal Health
January 1, 2023 - December 1, 2024Engineered end-to-end AI/ML pipelines for risk scoring, churn prediction, fraud detection, telematics underwriting, and sentiment analysis using Python, PySpark, Scikit-Learn, XGBoost, and related tools.
ML Engineer at LT Mindtree
July 1, 2020 - December 1, 2022Built end-to-end Azure ML projects and enterprise-grade AI services, including NLP, voice bot pipelines, and MLOps workflows, enabling scalable deployments, monitoring, and governance.
Education
Master of Science in Computer Science at University of Texas at Arlington
January 1, 2023 - December 1, 2024Master of Science in Computer Science at University of Texas at Arlington
January 1, 2023 - December 1, 2024Master's in Computer Science at University of Texas at Arlington
January 1, 2023 - December 1, 2024Master of Science in Computer Science at University of Texas at Arlington
January 1, 2023 - December 31, 2024Masters in Computer Science at University of Texas at Arlington
January 1, 2023 - December 31, 2024Master's in Computer Science at University of Texas at Arlington
January 1, 2023 - December 31, 2024Bachelor of Technology in Computer Science at DNR College of Engineering and Technology
June 1, 2017 - June 1, 2021Bachelor of Technology in Computer Science at DNR College of Engineering and Technology, Bhimavaram, India
June 1, 2017 - June 1, 2021Master of Science in Computer Science at University of Texas at Arlington
January 1, 2023 - December 1, 2024Master of Science in Computer Science at University of Texas at Arlington, TX, USA
January 1, 2023 - December 31, 2024Bachelor of Technology in Computer Science at DN R College of Engineering and Technology, Bhimavaram, India
June 1, 2017 - June 1, 2021Master of Science in Computer Science at University of Texas at Arlington
January 1, 2023 - December 1, 2024Bachelor of Technology in Computer Science at DNR College of Engineering and Technology, Bhimavaram, India
June 1, 2017 - June 1, 2021Qualifications
Industry Experience
Software & Internet, Professional Services, Telecommunications, Healthcare, Media & Entertainment, Education, Life Sciences, Computers & Electronics
Skills
Experience Level
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Hire a Full Stack Developer
We have the best full stack developer experts on Twine. Hire a full stack developer in Arlington today.