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

I’m Durga Prasad Jinna, an AI/ML engineer and data scientist with 8+ years of experience building production-grade machine learning and Generative AI solutions. I focus on NLP and LLM applications—especially RAG (Retrieval-Augmented Generation), document intelligence, semantic search, embeddings, and agentic workflows—using tools like LangChain/LangGraph, Amazon Bedrock, and Hugging Face Transformers. I enjoy turning messy enterprise data into reliable, scalable products by designing end-to-end pipelines (data prep, training, evaluation, deployment, monitoring). Across healthcare, financial services, and retail, I’ve shipped transformer-based NLP models, fraud and risk scoring systems, and knowledge assistants—while also emphasizing quality, latency, and responsible AI practices like evaluation and observability.…I’m Durga Prasad Jinna, an AI/ML engineer and data scientist with 8+ years of experience building production-grade machine learning and Generative AI solutions. I focus on NLP and LLM applications—especially RAG (Retrieval-Augmented Generation), document intelligence, semantic search, embeddings, and agentic workflows—using tools like LangChain/LangGraph, Amazon Bedrock, and Hugging Face Transformers. I enjoy turning messy enterprise data into reliable, scalable products by designing end-to-end pipelines (data prep, training, evaluation, deployment, monitoring). Across healthcare, financial services, and retail, I’ve shipped transformer-based NLP models, fraud and risk scoring systems, and knowledge assistants—while also emphasizing quality, latency, and responsible AI practices like evaluation and observability.

Durga Prasad Jinna

AI Engineer, Data Scientist, Data Engineer, +3





I’m Durga Prasad Jinna, an AI/ML engineer and data scientist with 8+ years of experience building production-grade machine learning and Generative AI solutions. I focus on NLP and LLM applications—especially RAG (Retrieval-Augmented Generation), document intelligence, semantic search, embeddings, and agentic workflows—using tools like LangChain/LangGraph, Amazon Bedrock, and Hugging Face Transformers. I enjoy turning messy enterprise data into reliable, scalable products by designing end-to-end pipelines (data prep, training, evaluation, deployment, monitoring). Across healthcare, financial services, and retail, I’ve shipped transformer-based NLP models, fraud and risk scoring systems, and knowledge assistants—while also emphasizing quality, latency, and responsible AI practices like evaluation and observability.…I’m Durga Prasad Jinna, an AI/ML engineer and data scientist with 8+ years of experience building production-grade machine learning and Generative AI solutions. I focus on NLP and LLM applications—especially RAG (Retrieval-Augmented Generation), document intelligence, semantic search, embeddings, and agentic workflows—using tools like LangChain/LangGraph, Amazon Bedrock, and Hugging Face Transformers. I enjoy turning messy enterprise data into reliable, scalable products by designing end-to-end pipelines (data prep, training, evaluation, deployment, monitoring). Across healthcare, financial services, and retail, I’ve shipped transformer-based NLP models, fraud and risk scoring systems, and knowledge assistants—while also emphasizing quality, latency, and responsible AI practices like evaluation and observability.

Available to hire

I’m Durga Prasad Jinna, an AI/ML engineer and data scientist with 8+ years of experience building production-grade machine learning and Generative AI solutions. I focus on NLP and LLM applications—especially RAG (Retrieval-Augmented Generation), document intelligence, semantic search, embeddings, and agentic workflows—using tools like LangChain/LangGraph, Amazon Bedrock, and Hugging Face Transformers.

I enjoy turning messy enterprise data into reliable, scalable products by designing end-to-end pipelines (data prep, training, evaluation, deployment, monitoring). Across healthcare, financial services, and retail, I’ve shipped transformer-based NLP models, fraud and risk scoring systems, and knowledge assistants—while also emphasizing quality, latency, and responsible AI practices like evaluation and observability.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Language

English

Advanced

Work Experience

Senior Data Scientist / AI-ML Engineer at Amazon

August 1, 2026 - Present

Designed and developed enterprise-grade agentic AI applications and RAG pipelines using Python, LangChain, LangGraph, LLMs, embeddings, and retrieval workflows to automate knowledge-intensive tasks. Built autonomous AI agents for planning, reasoning, tool calling, workflow execution, and multi-step orchestration across enterprise data and services. Implemented production-ready RAG architectures including document ingestion, chunking, metadata enrichment, vector embeddings, semantic retrieval, reranking, prompt engineering, and grounded response generation. Delivered scalable ML pipelines covering data preparation, feature engineering, training, evaluation, deployment, and monitoring with feedback loops. Developed AI/ML microservices using FastAPI, Docker, and Kubernetes, emphasizing reliability, latency, and fault tolerance. Integrated with SQL/NoSQL systems, search platforms, and vector stores, and implemented evaluation/observability using LangSmith and MLflow. Applied security/gover

Machine Learning Engineer at Bank of America

March 1, 2024 - December 31, 2025

Designed and fine-tuned Transformer-based NLP models (BERT/RoBERTa/DistilBERT) for document classification, sentiment analysis, intent detection, and customer complaint routing, improving accuracy by 22%. Built fraud detection and risk scoring models using XGBoost, Random Forest, Decision Trees, and boosting with feature engineering on large transaction datasets to reduce false positives and enable proactive risk monitoring. Developed customer segmentation and behavioral analytics using K-Means, PCA, Logistic Regression, and supervised learning for persona discovery and improved targeting. Created end-to-end ML pipelines for ingestion, preprocessing, feature engineering, training, validation, deployment, and monitoring. Implemented enterprise RAG/LLM workflows with embeddings, semantic/hybrid retrieval, and prompt engineering plus retrieval optimization. Built REST APIs/microservices with FastAPI and containerized services using Docker and Kubernetes; used MLflow and Git-based CI/CD fo

Data Scientist / Machine Learning Engineer at Elevance Health

November 1, 2021 - February 29, 2024

Developed production-grade machine learning solutions for healthcare analytics including prediction, classification, forecasting, and decision-support use cases. Built scalable data science pipelines using Python, Pandas, NumPy, SQL, and PySpark with data cleaning, exploratory analysis, feature engineering, and selection. Trained and tuned classification/regression models using scikit-learn and XGBoost, optimizing for business-aligned metrics. Applied deep learning and NLP using PyTorch and Hugging Face Transformers for text classification, entity extraction, document processing, and automation. Designed NLP/LLM-enabled workflows using embeddings, semantic search, retrieval, and prompt engineering. Delivered reusable ML services and APIs using FastAPI, containerized with Docker, and deployed via CI/CD. Implemented MLflow-based tracking and model lifecycle management and set up monitoring for performance and data quality in production.

Data Engineer / Data Analyst at Zion Infosystem

February 1, 2019 - July 31, 2021

Designed and developed data engineering and analytics pipelines using Python, SQL, Pandas, NumPy, and PySpark to support machine learning and BI initiatives. Built ETL/ELT workflows including ingestion, transformation, cleansing, and validation for structured and semi-structured datasets. Optimized SQL queries and created analytical datasets to support downstream predictive analytics. Performed data profiling, EDA, feature/statistical analysis, and implemented Python automation to reduce manual preparation. Collaborated with data scientists and application teams on schemas, transformations, and validation rules, and used Git-based development with documentation to maintain pipeline reliability and maintainability.

Data Engineer at Revalsys Technologies

March 1, 2018 - January 31, 2019

Built Python- and SQL-based ETL and data processing pipelines to collect, transform, validate, and integrate data from multiple sources. Used Pandas, NumPy, and Python for cleansing, transformation, and analysis to support downstream analytics. Designed and optimized database schemas and SQL transformation workflows; implemented automated data quality checks for missing/duplicate/inconsistent/anomalous records. Supported scalable data-processing workflows and coordinated with development teams to integrate data services with enterprise applications. Developed reusable utilities and automation scripts and applied Git-based source control, documentation, and testing practices.