Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I am Jagan Adari, a GenAI/AI/ML engineer who designs, builds, and deploys end-to-end AI solutions. I specialize in RAG, agentic AI, and production-grade systems using LangChain, GPT-4 (Azure/AWS), FastAPI/Python, React/Next.js, and vector databases. I have hands-on experience delivering scalable MLOps on AWS and Azure, with a track record of improving forecast accuracy and driving business impact. Beyond coding, I thrive at the intersection of business goals and responsible AI, collaborating with cross-functional teams to ensure privacy, governance, and observability in AI systems. I enjoy turning complex data into actionable insights and scalable AI applications that users love.…Hi, I am Jagan Adari, a GenAI/AI/ML engineer who designs, builds, and deploys end-to-end AI solutions. I specialize in RAG, agentic AI, and production-grade systems using LangChain, GPT-4 (Azure/AWS), FastAPI/Python, React/Next.js, and vector databases. I have hands-on experience delivering scalable MLOps on AWS and Azure, with a track record of improving forecast accuracy and driving business impact. Beyond coding, I thrive at the intersection of business goals and responsible AI, collaborating with cross-functional teams to ensure privacy, governance, and observability in AI systems. I enjoy turning complex data into actionable insights and scalable AI applications that users love.

Jagan Adari

Full Stack Developer, AI Engineer, Developer, +5





Hi, I am Jagan Adari, a GenAI/AI/ML engineer who designs, builds, and deploys end-to-end AI solutions. I specialize in RAG, agentic AI, and production-grade systems using LangChain, GPT-4 (Azure/AWS), FastAPI/Python, React/Next.js, and vector databases. I have hands-on experience delivering scalable MLOps on AWS and Azure, with a track record of improving forecast accuracy and driving business impact. Beyond coding, I thrive at the intersection of business goals and responsible AI, collaborating with cross-functional teams to ensure privacy, governance, and observability in AI systems. I enjoy turning complex data into actionable insights and scalable AI applications that users love.…Hi, I am Jagan Adari, a GenAI/AI/ML engineer who designs, builds, and deploys end-to-end AI solutions. I specialize in RAG, agentic AI, and production-grade systems using LangChain, GPT-4 (Azure/AWS), FastAPI/Python, React/Next.js, and vector databases. I have hands-on experience delivering scalable MLOps on AWS and Azure, with a track record of improving forecast accuracy and driving business impact. Beyond coding, I thrive at the intersection of business goals and responsible AI, collaborating with cross-functional teams to ensure privacy, governance, and observability in AI systems. I enjoy turning complex data into actionable insights and scalable AI applications that users love.

Available to hire

Hi, I am Jagan Adari, a GenAI/AI/ML engineer who designs, builds, and deploys end-to-end AI solutions. I specialize in RAG, agentic AI, and production-grade systems using LangChain, GPT-4 (Azure/AWS), FastAPI/Python, React/Next.js, and vector databases. I have hands-on experience delivering scalable MLOps on AWS and Azure, with a track record of improving forecast accuracy and driving business impact.

Beyond coding, I thrive at the intersection of business goals and responsible AI, collaborating with cross-functional teams to ensure privacy, governance, and observability in AI systems. I enjoy turning complex data into actionable insights and scalable AI applications that users love.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

Javanese

Advanced

English

Fluent

Work Experience

Gen AI Engineer at Walgreens

December 1, 2024 - Present

Developed full-stack generative AI web applications integrating React.js, TypeScript, and FastAPI with Azure OpenAI for real-time document summarization and conversational Q&A. Built RAG pipelines using LangChain, Azure Cognitive Search, and Blob Storage, designed custom GPT agents leveraging Function Calling, and implemented chatbot UIs with real-time token streaming for improved user experience. Fine-tuned and deployed LLMs via Azure Machine Learning and Amazon SageMaker, containerized applications with Docker on AKS, and set up CI/CD pipelines alongside monitoring tools. Reduced latency and hallucinations in AI responses, enforced enterprise authentication with Azure AD B2C, and ensured Responsible AI compliance through prompt safety and data privacy controls.

LLM Engineer at US Bank

December 1, 2024 - August 21, 2025

Designed LLM-powered applications using GPT-4 via AWS Bedrock and LangChain for document summarization, intelligent search, and virtual assistants. Built RAG pipelines with FAISS and Amazon OpenSearch supporting secure answers over private datasets. Conducted model training and fine-tuning with Amazon SageMaker and MLflow, orchestrated serverless AI workflows with AWS Lambda and Step Functions, and integrated vector semantic search with Qdrant and Pinecone. Containerized and deployed GenAI services on Amazon EKS with autoscaling, logging, and monitoring. Developed full-stack GenAI web apps, engineered secure data pipelines with AWS Glue and Redshift, and collaborated on CI/CD and Responsible AI compliance.

AI/ML Engineer at Accenture

December 1, 2023 - August 21, 2025

Developed and deployed predictive machine learning models for forecasting and classification using Python, scikit-learn, and XGBoost. Designed data preprocessing pipelines with Pandas and NumPy, built end-to-end ML workflows on AWS SageMaker, and implemented feature engineering to improve model performance. Collaborated with data engineering teams for data ingestion via AWS Glue and PySpark, automated experiment tracking with MLflow, and containerized models with Docker integrated into CI/CD pipelines. Set up monitoring and alerting for model drift, conducted A/B testing, and ensured compliance with data security and PII regulations. Documented architectures and worked in Agile teams for smooth production rollouts.

Gen AI Engineer at Walgreens

December 1, 2024 - Present

Developed full-stack generative AI web applications using React.js, TypeScript, and FastAPI with Azure OpenAI services for real-time document summarization and conversational Q&A. Built retrieval-augmented generation pipelines with LangChain, Azure Cognitive Search, and Azure Blob Storage to provide accurate, context-rich answers. Designed custom GPT agents utilizing Function Calling for multi-step task automation. Implemented secure enterprise authentication with Azure AD B2C and managed secrets in Azure Key Vault. Containerized and deployed applications on Azure Kubernetes Service with CI/CD pipelines. Reduced latency by 35% and hallucinations by 28% through optimization and prompt tuning. Collaborated on Responsible AI compliance ensuring prompt safety, data privacy, and audit logging.

LLM Engineer at US Bank

December 1, 2024 - August 21, 2025

Designed AI applications powered by GPT-4 via AWS Bedrock and LangChain for document summarization and intelligent search. Built secure retrieval-augmented generation pipelines using FAISS, Amazon OpenSearch, and S3. Fine-tuned models on Amazon SageMaker with automated hyperparameter tuning and MLflow tracking. Orchestrated serverless AI workflows with AWS Lambda and Step Functions. Developed vector semantic search using Qdrant and Pinecone integrated via LangChain. Containerized services and deployed on Amazon EKS with autoscaling and monitoring via CloudWatch and Prometheus. Delivered full-stack GenAI web apps and chat-based analytics dashboards secured with AWS Cognito and WebSockets. Established secure data pipelines using AWS Glue, Athena, PySpark, and Redshift. Partnered with DevOps for CI/CD and enforced Responsible AI standards.

AI/ML Engineer at Accenture

December 1, 2023 - August 21, 2025

Developed predictive models using Python, scikit-learn, and XGBoost in production environments. Built data preprocessing pipelines with Pandas and NumPy. Managed end-to-end ML workflows on AWS SageMaker including training, tuning, packaging, and deployment to scalable endpoints. Engineered features to improve model generalization and collaborated on data ingestion with AWS Glue and PySpark. Automated experiment tracking with MLflow. Exposed models as REST services with Flask and FastAPI, integrated Docker, and supported CI/CD workflows. Set up performance monitoring and alerting with CloudWatch and performed A/B testing to assess business impact. Ensured data security and compliance for PII. Documented architecture and ran projects in Agile teams.

Gen AI Engineer at Walgreens USA

December 1, 2024 - November 5, 2025

Developed full-stack GenAI web applications with React/TypeScript and FastAPI/Python; integrated Azure OpenAI for real-time document summarization and Q&A; built RAG pipelines with LangChain, Azure Cognitive Search, and Azure Blob Storage; designed custom GPT agents for multi-step automation; created real-time chat UIs with token streaming via WebSockets; fine-tuned and served LLMs via Azure ML and Amazon SageMaker; deployed containerized apps on AKS with CI/CD and monitoring; enhanced security with Azure AD B2C and Key Vault; extracted structured data from PDFs using Form Recognizer; collaborated on Responsible AI compliance.

LLM Engineer at US Bank USA

December 1, 2024 - December 1, 2024

Designed and developed LLM-powered applications using GPT-4 (AWS Bedrock) and LangChain for document summarization, contextual search, and virtual assistant use cases; built RAG pipelines with FAISS, OpenSearch, and S3; trained and fine-tuned models on SageMaker; orchestrated serverless AI workflows with Lambda, Step Functions, and API Gateway; implemented vector retrieval with Qdrant and Pinecone; containerized services on EKS with autoscaling and observability; supported high traffic (up to 120 rps); built full-stack GenAI apps with React/TypeScript and FastAPI; implemented secure data pipelines with AWS Glue, Athena, PySpark, and Redshift; established CI/CD via CodePipeline/CloudFormation; ensured Responsible AI governance and audit logging.

AI/ML Engineer at Accenture India

December 1, 2023 - December 1, 2023

Developed predictive models using Python, scikit-learn, and XGBoost; built end-to-end ML pipelines with Pandas, NumPy, and PySpark; managed AWS SageMaker training, deployment, and automated hyperparameter tuning; tracked experiments with MLflow and maintained model versioning; exposed models via Flask/FastAPI REST services; containerized with Docker and deployed through CI/CD; monitored for drift and performance; ensured security/compliance for PII data and documented architectures and runbooks.

Gen AI Engineer at Walgreens USA

December 1, 2024 - November 7, 2025

Developed full-stack GenAI web applications using React/TypeScript (frontend) and FastAPI/Python (backend), integrating Azure OpenAI (GPT-4) for real-time document summarization and conversational Q&A. Built Retrieval-Augmented Generation (RAG) pipelines with LangChain, Azure Cognitive Search, and Azure Blob Storage, enabling context-rich enterprise Q&A over internal knowledge bases. Designed and deployed custom GPT agents leveraging Function Calling and LangChain tools to automate multi-step tasks such as form filling, report generation, and data retrieval. Created real-time chatbot UIs with token-level streaming via WebSockets, improving responsiveness and session memory management. Fine-tuned and served LLMs via Azure Machine Learning and Amazon SageMaker in a hybrid setup for HR automation, legal document analysis, and IT support workflows. Deployed containerized GenAI applications on AKS, set up CI/CD pipelines with GitHub Actions, and monitored performance with Azure Monitor and