Available to hire
I’m Kranthi Kumar Karupati, a Generative AI Engineer with 5+ years of experience designing and deploying end-to-end machine learning and LLM-driven solutions. I specialize in building RAG pipelines, prompt engineering, and multi-agent systems using OpenAI GPT, LLaMA, and Azure OpenAI. I have a strong background in NLP, computer vision, and deep learning with tools like TensorFlow, PyTorch, and Hugging Face. I’m proficient in ML Ops and deploying scalable AI solutions across Azure, AWS, and GCP, with CI/CD, Docker, and Kubernetes.
I’m passionate about integrating AI into enterprise systems, delivering intelligent chat and voice solutions, and collaborating with cross-functional teams to create secure, reliable GenAI applications for finance, healthcare, and beyond.
Skills
Language
Javanese
Intermediate
Bashkir
Advanced
Afar
Intermediate
Work Experience
Gen AI Engineer at U.S. Bank
February 1, 2024 - November 18, 2025Delivered LLM-powered applications using OpenAI GPT, Anthropic Claude, Google Gemini, and LLaMA for chatbots, text summarization, and automated decision workflows. Advanced prompt engineering (few-shot, zero-shot, chain-of-thought, function-calling) to improve output relevance. Designed Retrieval-Augmented Generation (RAG) pipelines with LangChain and Amazon OpenSearch, including vector embeddings via text-embedding-3-large for semantic search and efficient retrieval. Built multi-agent architectures with LangChain Agents and LangGraph to automate complex tasks. Integrated LLMs into enterprise chat/voice solutions, including IVR systems and Amazon Lex. Finetuned open-source LLMs (LLaMA, Mistral) with LoRA on Amazon SageMaker. Developed backend services with Python, FastAPI, and REST, orchestrated via AWS Lambda and API Gateway. Deployed GenAI solutions on AWS (SageMaker, Bedrock) with containerized endpoints (ECS/EKS). Implemented CI/CD with CodePipeline, Docker, and EKS; monitored late
AI/ML Engineer at Accenture - Hyderabad, India
December 1, 2023 - December 1, 2023Designed and deployed end-to-end ML pipelines on AWS SageMaker for classification, prediction, and recommendation systems. Built NLP and time-series models using TensorFlow and PyTorch, addressing data imbalance, drift, and model drift in production. Implemented NLP tasks like sentiment analysis, NER, and document summarization in real-time applications. Integrated ML models into production via REST APIs (FastAPI) deployed with AWS Lambda and API Gateway. Built data ingestion/processing pipelines using AWS Glue, Kinesis Data Streams, and Lambda for real-time and batch workflows. Implemented MLOps with SageMaker Model Monitor and MLflow, enabling automated versioning and deployment with rollback. Containerized services with Docker and deployed on EKS. Monitored performance with CloudWatch, Prometheus, and Grafana; set up automated retraining pipelines. Collaborated with cross-functional teams to ensure security and governance; performed hyperparameter tuning with SageMaker Automatic Mod
Data Scientist/ ML Engineer at Accenture - Hyderabad, India
August 1, 2022 - August 1, 2022Built ML models for healthcare and enterprise domains, including classification, regression, clustering, and NLP tasks using Scikit-Learn, XGBoost, and TensorFlow/PyTorch. Led data exploration, feature engineering, and model evaluation (precision, recall, ROC-AUC). Implemented ETL/real-time data workflows with Apache Spark, Hadoop, and Databricks. Deployed ML models via Flask/FastAPI REST APIs and integrated with enterprise systems. Created interactive dashboards with Power BI and Plotly. Addressed data quality, feature drift, and latency with automated retraining and real-time feature validation on AWS SageMaker Processing.
Gen AI Engineer at U.S. Bank
February 1, 2024 - November 25, 2025Led design and deployment of LLM-powered applications using OpenAI GPT, Anthropic Claude, Google Gemini, and LLaMA for chatbots, text summarization, and automated decision-making workflows. Implemented advanced prompt strategies (few-shot, zero-shot, chain-of-thought, and function calling) to improve output relevance and reliability. Built Retrieval-Augmented Generation (RAG) pipelines with LangChain and Amazon OpenSearch, enabling contextual, domain-aware responses, and generated high-quality vector embeddings for semantic search. Created multi-agent architectures with LangChain Agents and LangGraph to automate complex tasks and enhance decision-making with LLMs. Integrated LLMs into enterprise chat and voice solutions, including IVR systems and Amazon Lex, to improve customer engagement. Fine-tuned open-source LLMs (LLaMA, Mistral) with LoRA for domain-specific inference on SageMaker. Developed scalable backend services in Python with FastAPI and REST APIs, orchestrated via AWS Lambd
AI/ML Engineer at Accenture - Hyderabad INDIA
December 1, 2023 - December 1, 2023Designed and deployed end-to-end ML pipelines on AWS SageMaker for classification, prediction, and recommendation systems, ensuring scalable and secure model hosting. Built and optimized deep learning models for NLP and time-series forecasting with TensorFlow and PyTorch; addressed data imbalance and drift in production. Integrated ML models into production systems via RESTful APIs with FastAPI, deployed on AWS Lambda and API Gateway for low-latency inference. Developed and maintained scalable data ingestion and processing pipelines using AWS Glue, Kinesis Data Streams, and Lambda to support real-time and batch workflows. Implemented MLOps workflows with AWS CodePipeline, SageMaker Model Monitor, and MLflow for automated versioning, continuous integration, and deployment with rollback. Containerized ML services with Docker and deployed on AWS EKS for reliable production environments. Monitored performance and infrastructure health with CloudWatch, Prometheus, and Grafana; set up alerts
Data Scientist/ ML Engineer at Accenture - Hyderabad INDIA
August 1, 2022 - August 1, 2022Built and maintained ML models for classification, regression, and clustering using Scikit-learn, XGBoost, and TensorFlow on scalable cloud infrastructure. Conducted EDA and feature engineering with Pandas, NumPy, and Matplotlib to uncover data patterns and improve model accuracy. Designed and implemented ETL and real-time data workflows using Apache Spark, Hadoop, and Databricks. Developed NLP models for sentiment analysis, text classification, and named entity recognition using spaCy, NLTK, and Hugging Face Transformers; deployed in production pipelines. Created and maintained dashboards with Power BI and Plotly to deliver actionable insights. Deployed ML models via Flask and FastAPI, integrating with enterprise systems through scalable REST APIs. Utilized SQL to query large datasets and prepare data views for machine learning workflows. Collaborated with data engineers and business analysts to deliver AI-powered solutions in healthcare and insurance. Evaluated model performance with
AI/ML Engineer at Accenture
August 1, 2022 - December 1, 2023Designed and deployed end-to-end ML pipelines on AWS SageMaker for NLP and time-series forecasting; built and optimized models using TensorFlow and PyTorch; integrated NLP solutions into real-time applications with Hugging Face Transformers; implemented MLOps with AWS CodePipeline, SageMaker Model Monitor, and MLflow; containerized services with Docker and deployed on EKS; built REST APIs with FastAPI and ensured secure, scalable production deployment; implemented monitoring with CloudWatch, Prometheus, and Grafana; managed data ingestion via AWS Glue and Kinesis.
Data Scientist / ML Engineer at Accenture
July 1, 2020 - August 1, 2022Built NLP and time-series models using Scikit-learn, XGBoost, TensorFlow, and PyTorch; conducted EDA, feature engineering, and model evaluation; implemented ETL and real-time data workflows with Apache Spark/Hadoop/Databricks; deployed ML models via Flask/FastAPI REST APIs; supported data governance and security in healthcare/insurance domains; collaborated with data engineers and business analysts to deliver AI-powered solutions; created dashboards with Power BI and Plotly.
AI/ML Engineer at Accenture - Hyderabad
August 1, 2022 - December 1, 2023Designed and deployed end-to-end machine learning pipelines on AWS SageMaker for classification, prediction, and recommendations, ensuring scalable model hosting and secure access. Built and optimized NLP and time-series models with TensorFlow and PyTorch, addressing data imbalance and model drift in production. Implemented NLP techniques such as sentiment analysis, named entity recognition, and document summarization using Hugging Face Transformers, integrating models into real-time applications. Integrated ML models into production via RESTful APIs built with FastAPI and serverless deployment on AWS Lambda and API Gateway. Developed scalable data ingestion and processing pipelines using AWS Glue, Kinesis Data Streams, and Lambda to support real-time and batch processing. Established MLOps workflows with SageMaker Model Monitor and MLflow for automated versioning, CI/CD, and controlled deployments with rollback. Monitored data and model performance with CloudWatch, Prometheus, and Gra
Data Scientist/ ML Engineer at Accenture - Hyderabad
July 1, 2020 - August 1, 2022Built and deployed ML models for classification, regression, and clustering using Scikit-learn, XGBoost, and TensorFlow on cloud-scale infrastructure. Conducted EDA and feature engineering with Pandas, NumPy, and Matplotlib. Designed and implemented ETL and real-time data workflows using Apache Spark, Hadoop, and Databricks. Developed NLP models for sentiment analysis, text classification, and named entity recognition using spaCy, NLTK, and Hugging Face Transformers, deployed in production pipelines. Created dashboards in Power BI and Plotly to deliver actionable insights. Deployed ML models via Flask and FastAPI, integrating with enterprise systems through scalable REST APIs. Used SQL for data querying and preparation. Collaborated with data engineers and business analysts to deliver solutions for healthcare and insurance. Evaluated models with confusion matrix, ROC-AUC; performed hyperparameter tuning with grid search and manual tuning; maintained reproducibility and governance.
Education
Master's at Eastern Illinois University, Charleston, United States
January 11, 2030 - May 1, 2025Bachelor's at Singhania University, India
January 11, 2030 - May 1, 2021Master's at Eastern Illinois University
January 11, 2030 - May 1, 2025Bachelor's at Singhania University
January 11, 2030 - May 1, 2021Master's degree at Eastern Illinois University, Charleston, United States
January 11, 2030 - May 1, 2025Bachelor's degree at Singhania University, India
January 11, 2030 - May 1, 2021Master's at Eastern Illinois University
January 11, 2030 - May 1, 2025Bachelor's at Singhania University
January 11, 2030 - May 1, 2021Qualifications
Industry Experience
Software & Internet, Financial Services, Professional Services, Education, Healthcare, Media & Entertainment
Skills
Hire a AI Engineer
We have the best ai engineer experts on Twine. Hire a ai engineer in Charleston today.