Open to opportunities

Keerthika Khanapuram

@keerthikakhanapuram

Message

Senior AI/ML engineer specializing in GenAI, RAG, and production-grade MLOps on cloud platforms.

United States

Message

What I'm looking for

I’m looking for a role where I can lead production-grade GenAI/LLM systems—RAG, chatbots, and MLOps—with real-time pipelines, model monitoring/drift detection, and Responsible AI in cloud-native environments.

I’m a Senior AI/ML Engineer with 8 years of experience designing and deploying enterprise-scale Artificial Intelligence (AI), Machine Learning (ML), Generative AI, Large Language Models (LLMs), Agentic AI, and MLOps solutions. I focus on building AI-powered applications that are production-ready and resilient in real environments.

I build LLM-powered workflows—especially RAG (Retrieval-Augmented Generation), AI chatbots, conversational AI, semantic search, and knowledge retrieval—using frameworks like LangChain, LangGraph, and LlamaIndex. I fine-tune models with LoRA/QLoRA, generate embeddings, and power contextual responses with vector databases such as Milvus and Weaviate. I also implement end-to-end real-time pipelines and scalable deployment using Python, PyTorch, TensorFlow, FastAPI, Kafka, Spark Structured Streaming, Docker, Kubernetes, and CI/CD.

I deliver MLOps with MLflow, Kubeflow, Airflow, and automated training/deployment/monitoring, including drift detection and Responsible AI. Across Healthcare and Finance, I’ve implemented explainable AI with SHAP/LIME and governance needs aligned with requirements like GDPR and PCI-DSS, while partnering with engineering and business stakeholders to ship scalable cloud-native AI platforms.

Experience

Work history, roles, and key accomplishments

Current

AI/ML Data Engineer

Current

Sentara Health

Jan 2025 - Present (1 year 5 months)

Designed and deployed end-to-end AI/ML and Generative AI solutions on GCP for fraud detection, credit risk modeling, and predictive analytics. Built RAG pipelines with Milvus/Weaviate, implemented real-time streaming workflows with Kafka and Spark, and delivered MLOps for deployment, monitoring, drift detection, and Responsible AI.

Python GCP RAG Milvus Weaviate Kafka Spark Structured Streaming fastAPI MLFlow SHAP

AI/ML Engineer

Denta Quest

Nov 2023 - Dec 2024 (1 year 1 month)

Delivered end-to-end AI/ML and LLM workflows across data ingestion, modeling, evaluation, deployment, and monitoring. Integrated OpenAI, Claude, and Gemini for chatbots and semantic search, built RAG systems with vector embeddings, and fine-tuned transformer models using LoRA/QLoRA.

Python LLM OpenAI API LlamaIndex RAG PyTorch OpenCV

Senior Data Engineer

Value Labs

Dec 2022 - Sep 2023 (9 months)

Designed and developed ETL pipelines using Python, SQL, and Apache Spark for batch and real-time data processing. Built data workflows with Kafka and Airflow, optimized SQL performance, and delivered reporting dashboards using Power BI and Tableau.

Python SQL Apache Spark Kafka Airflow AWS S3 AWS RDS ETL ELT Power BI Tableau

Senior Data Engineer

NTT Data

Jun 2019 - Nov 2022 (3 years 5 months)

Built and maintained scalable ETL/ELT pipelines for ingesting and transforming structured and unstructured data into AWS Data Lakes and Warehouses. Developed reusable Python data utilities, engineered feature-ready datasets for AI/ML workloads, and implemented automated data validation and monitoring with CloudWatch.

AWS Glue Amazon S3 Amazon Redshift AWS Cloudwatch Python Pandas NumPy Apache Kafka Tableau

Data Engineer

Glaxo Smith Kline

Jun 2018 - May 2019 (11 months)

Implemented scalable ETL/ELT pipelines using AWS Glue, AWS Lambda, and Amazon Redshift to support AI/ML workloads. Built data lake and warehouse schemas for improved query performance, and applied data quality frameworks, optimization, and feature engineering for reliable analytics and model-ready datasets.