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

I am a Senior AI Engineer with 11+ years of experience designing, deploying, and scaling production-grade AI and LLM-powered systems. I specialize in Generative AI, Retrieval-Augmented Generation (RAG), and agentic AI workflows for enterprise automation. I have hands-on experience building scalable LLM applications across AWS and GCP, with expertise in multi-agent orchestration, tool-calling, and contextual memory management. I design semantic search pipelines with FAISS and Pinecone, evaluate LLMs for safety, and deploy low-latency inference services via FastAPI, Docker, and Kubernetes. I love translating complex business requirements into production-ready AI that delivers measurable impact.…I am a Senior AI Engineer with 11+ years of experience designing, deploying, and scaling production-grade AI and LLM-powered systems. I specialize in Generative AI, Retrieval-Augmented Generation (RAG), and agentic AI workflows for enterprise automation. I have hands-on experience building scalable LLM applications across AWS and GCP, with expertise in multi-agent orchestration, tool-calling, and contextual memory management. I design semantic search pipelines with FAISS and Pinecone, evaluate LLMs for safety, and deploy low-latency inference services via FastAPI, Docker, and Kubernetes. I love translating complex business requirements into production-ready AI that delivers measurable impact.

Divya Kota

AI Engineer, Data Scientist, Full Stack Developer, +2





I am a Senior AI Engineer with 11+ years of experience designing, deploying, and scaling production-grade AI and LLM-powered systems. I specialize in Generative AI, Retrieval-Augmented Generation (RAG), and agentic AI workflows for enterprise automation. I have hands-on experience building scalable LLM applications across AWS and GCP, with expertise in multi-agent orchestration, tool-calling, and contextual memory management. I design semantic search pipelines with FAISS and Pinecone, evaluate LLMs for safety, and deploy low-latency inference services via FastAPI, Docker, and Kubernetes. I love translating complex business requirements into production-ready AI that delivers measurable impact.…I am a Senior AI Engineer with 11+ years of experience designing, deploying, and scaling production-grade AI and LLM-powered systems. I specialize in Generative AI, Retrieval-Augmented Generation (RAG), and agentic AI workflows for enterprise automation. I have hands-on experience building scalable LLM applications across AWS and GCP, with expertise in multi-agent orchestration, tool-calling, and contextual memory management. I design semantic search pipelines with FAISS and Pinecone, evaluate LLMs for safety, and deploy low-latency inference services via FastAPI, Docker, and Kubernetes. I love translating complex business requirements into production-ready AI that delivers measurable impact.

Available to hire

I am a Senior AI Engineer with 11+ years of experience designing, deploying, and scaling production-grade AI and LLM-powered systems. I specialize in Generative AI, Retrieval-Augmented Generation (RAG), and agentic AI workflows for enterprise automation.

I have hands-on experience building scalable LLM applications across AWS and GCP, with expertise in multi-agent orchestration, tool-calling, and contextual memory management. I design semantic search pipelines with FAISS and Pinecone, evaluate LLMs for safety, and deploy low-latency inference services via FastAPI, Docker, and Kubernetes. I love translating complex business requirements into production-ready AI that delivers measurable impact.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Work Experience

AI Engineer / Senior Data Scientist at Bank Of America

November 1, 2023 - Present

Architected production-grade LLM applications using GPT-4, Claude, and LLaMA with scalable Retrieval-Augmented Generation (RAG) frameworks. Delivered enterprise knowledge retrieval and automated summarization systems across multiple business units. Designed multi-agent AI workflows with LangChain including tool-calling and function orchestration, enabling contextual reasoning and human-in-the-loop controls for compliance. Built asynchronous FastAPI inference services for real-time responses; deployed agentic AI pipelines on AWS Bedrock with CI/CD and secure deployments. Containerized services with Docker on AWS ECS; integrated API Gateway and IAM for secure hosting. Engineered embedding pipelines using FAISS and Pinecone for semantic retrieval; implemented identity resolution and graph-based clustering to unify customer profiles across large datasets. Developed structured prompt frameworks and context injection to reduce hallucinations and improve grounded responses. Led LLM adoption a

Sr Data Scientist at Boeing

December 1, 2021 - October 1, 2023

Developed machine learning solutions using PyTorch and Scikit-learn for large-scale document classification and multi-label prediction across enterprise datasets. Designed feature engineering and similarity scoring pipelines to improve document matching, clustering, and contextual relationship discovery. Built statistical and ML models for structured and unstructured data to enhance analytical decision workflows. Implemented model optimization with hyperparameter tuning and cross-validation; built deep learning models for anomaly detection, classification, and predictive tasks. Processed large datasets with PySpark and distributed pipelines; implemented MLflow for experiment tracking and reproducibility. Optimized inference latency and collaborated with engineering teams to productionize ML models and implement monitoring.

Data Scientist at State of TN (DHS)

January 1, 2020 - November 1, 2021

Developed fraud detection and financial risk models using XGBoost and Random Forest. Built NLP pipelines for text classification and sentiment analysis to extract insights from citizen and policy data. Designed feature engineering workflows and prepared ML-ready datasets. Implemented Dockerized model deployment on AWS SageMaker; performed statistical validation with ROC-AUC and cross-validation. Built time-series forecasting models for operational trend analysis, automated data ingestion and preprocessing, and integrated models with backend APIs for real-time predictions. Implemented monitoring and retraining triggers to maintain model reliability.

Data Analyst at Charter Communications

August 1, 2018 - December 1, 2019

Developed customer segmentation models using clustering and classification to improve marketing and retention strategies. Built churn prediction models to enable proactive engagement and risk mitigation. Performed feature engineering and hyperparameter tuning, designed predictive analytics pipelines for telecom network optimization, and conducted exploratory data analysis to translate insights into actionable ML-driven strategies. Implemented anomaly detection for network performance, automated preprocessing, and collaborated with engineering for model integration and deployment.

Jr. Data Analyst at Modak Analytics

July 1, 2013 - September 1, 2017

Conducted exploratory data analysis, developed data preprocessing scripts, and assisted in building regression and classification models. Optimized SQL queries and data pipelines, performed data quality checks, and supported migration of large datasets to scalable environments. Collaborated with senior analysts on feature selection and helped build dashboards to communicate analytical findings.