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

I am a Senior AI/ML Engineer with 8 years of experience building and deploying enterprise-grade ML, Generative AI and data engineering solutions across healthcare, banking, telecom and analytics. I specialize in production-grade RAG systems for biomedical knowledge retrieval, fraud detection, AML compliance and risk analytics, using vector and hybrid search architectures. I have hands-on expertise in ML and NLP using Python, PyTorch, TensorFlow, Scikit-learn, SQL and transformer-based models such as BERT for classification and entity extraction. I have built scalable real-time and batch data pipelines with Spark, Kafka, AWS Glue and AWS Kinesis; deployed cloud-native AI systems on AWS SageMaker and Bedrock, Docker, Kubernetes and MLflow with CI/CD automation; and delivered explainable, compliant AI in regulated environments. I excel at translating complex business problems into scalable AI solutions that deliver measurable impact, collaborating with clinical, research and compliance teams to ensure safe, explainable adoption.…I am a Senior AI/ML Engineer with 8 years of experience building and deploying enterprise-grade ML, Generative AI and data engineering solutions across healthcare, banking, telecom and analytics. I specialize in production-grade RAG systems for biomedical knowledge retrieval, fraud detection, AML compliance and risk analytics, using vector and hybrid search architectures. I have hands-on expertise in ML and NLP using Python, PyTorch, TensorFlow, Scikit-learn, SQL and transformer-based models such as BERT for classification and entity extraction. I have built scalable real-time and batch data pipelines with Spark, Kafka, AWS Glue and AWS Kinesis; deployed cloud-native AI systems on AWS SageMaker and Bedrock, Docker, Kubernetes and MLflow with CI/CD automation; and delivered explainable, compliant AI in regulated environments. I excel at translating complex business problems into scalable AI solutions that deliver measurable impact, collaborating with clinical, research and compliance teams to ensure safe, explainable adoption.

Venkata Durga Kavya Bhatta

Data Scientist, AI Developer, AI Prompt Engineer, +2





I am a Senior AI/ML Engineer with 8 years of experience building and deploying enterprise-grade ML, Generative AI and data engineering solutions across healthcare, banking, telecom and analytics. I specialize in production-grade RAG systems for biomedical knowledge retrieval, fraud detection, AML compliance and risk analytics, using vector and hybrid search architectures. I have hands-on expertise in ML and NLP using Python, PyTorch, TensorFlow, Scikit-learn, SQL and transformer-based models such as BERT for classification and entity extraction. I have built scalable real-time and batch data pipelines with Spark, Kafka, AWS Glue and AWS Kinesis; deployed cloud-native AI systems on AWS SageMaker and Bedrock, Docker, Kubernetes and MLflow with CI/CD automation; and delivered explainable, compliant AI in regulated environments. I excel at translating complex business problems into scalable AI solutions that deliver measurable impact, collaborating with clinical, research and compliance teams to ensure safe, explainable adoption.…I am a Senior AI/ML Engineer with 8 years of experience building and deploying enterprise-grade ML, Generative AI and data engineering solutions across healthcare, banking, telecom and analytics. I specialize in production-grade RAG systems for biomedical knowledge retrieval, fraud detection, AML compliance and risk analytics, using vector and hybrid search architectures. I have hands-on expertise in ML and NLP using Python, PyTorch, TensorFlow, Scikit-learn, SQL and transformer-based models such as BERT for classification and entity extraction. I have built scalable real-time and batch data pipelines with Spark, Kafka, AWS Glue and AWS Kinesis; deployed cloud-native AI systems on AWS SageMaker and Bedrock, Docker, Kubernetes and MLflow with CI/CD automation; and delivered explainable, compliant AI in regulated environments. I excel at translating complex business problems into scalable AI solutions that deliver measurable impact, collaborating with clinical, research and compliance teams to ensure safe, explainable adoption.

Available to hire

I am a Senior AI/ML Engineer with 8 years of experience building and deploying enterprise-grade ML, Generative AI and data engineering solutions across healthcare, banking, telecom and analytics. I specialize in production-grade RAG systems for biomedical knowledge retrieval, fraud detection, AML compliance and risk analytics, using vector and hybrid search architectures. I have hands-on expertise in ML and NLP using Python, PyTorch, TensorFlow, Scikit-learn, SQL and transformer-based models such as BERT for classification and entity extraction.

I have built scalable real-time and batch data pipelines with Spark, Kafka, AWS Glue and AWS Kinesis; deployed cloud-native AI systems on AWS SageMaker and Bedrock, Docker, Kubernetes and MLflow with CI/CD automation; and delivered explainable, compliant AI in regulated environments. I excel at translating complex business problems into scalable AI solutions that deliver measurable impact, collaborating with clinical, research and compliance teams to ensure safe, explainable adoption.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

AI/ML Engineer – GenAI and RAG at AbbVie

July 1, 2025 - Present

Designed and implemented enterprise GenAI and RAG-based knowledge retrieval over 5M+ biomedical documents using LLaMA and GPT-4, with NLP-driven embeddings and semantic search to improve retrieval accuracy by 30%. Integrated Anthropic Claude models via AWS Bedrock, implementing prompt engineering, safety guardrails and controlled generation for compliant, reliable outputs. Built agentic AI workflows using LangChain with tool-calling and multi-step reasoning; implemented MCP-based tool orchestration to improve response completeness and execution accuracy by 20%. Built memory-enabled AI agents for contextual reasoning and traceability in regulated healthcare environments. Fine-tuned transformer models with LoRA/QLoRA; developed LLM evaluation and synthetic stress-testing to reduce unsafe outputs by 25%. Deployed GenAI microservices with Docker/Kubernetes; automated CI/CD with GitHub Actions and SageMaker; used S3 and OpenSearch for scalable inference and retrieval.

Data Engineer - Machine Learning & Analytics at AT&T

May 1, 2019 - December 31, 2023

Worked on large-scale telecom OSS/BSS data engineering and ML analytics initiatives focusing on network performance optimization, subscriber behavior analysis, KPI forecasting and anomaly detection. Built scalable Python/SQL automation and feature engineering pipelines; engineered large-scale data pipelines with Apache Spark, Kafka and Databricks to prepare ML-ready datasets. Implemented time-series forecasting with Prophet for KPI prediction and anomaly detection for proactive network optimization. Developed GenAI-based summarization pipelines; built lightweight RAG retrieval workflows over historical telecom data to enable contextual querying and faster root-cause analysis. Containerized ML and data pipelines with Docker for consistent deployment; collaborated on ETL and ML workflows with Airflow; supported model validation and UAT for analytics platforms.

Data Analyst at Dun & Bradstreet

May 1, 2017 - April 30, 2019

Worked on data analytics initiatives for commercial intelligence and credit risk assessment. Built structured data processing and analytics workflows for entity resolution, customer profiling and credit risk modeling. Conducted EDA on firmographic data and built ML models (Logistic Regression, Random Forest, XGBoost) for credit risk scoring, achieving 20–25% improvement in accuracy. Developed data validation and transformation workflows and automated reporting, reducing manual effort by up to 40%. Created dashboards to visualize credit risk trends and provided actionable insights for stakeholders.

Machine Learning Engineer – Fraud Detection & Risk Analytics at Wells Fargo

January 1, 2015 - June 30, 2025

Developed enterprise-scale fraud detection and GenAI-powered risk intelligence solutions supporting AML compliance, transaction monitoring and customer risk scoring. Built ML-based risk scoring pipelines (Python, PySpark, Scikit-learn) improving accuracy by 25% and reducing false positives. Engineered scalable batch and real-time data processing with AWS Glue, AWS Kinesis and Spark Structured Streaming for monitoring and anomaly detection. Applied hybrid ML and rule-based approaches for fraud detection and AML monitoring. Built GenAI-driven risk explanations using LLM-based summarization and RAG to generate contextual insights from regulatory, historical and transaction data. Deployed production-grade scoring and GenAI microservices with AWS SageMaker and Flask; established end-to-end MLOps with CI/CD, drift monitoring and performance tracking. Developed NLP-powered KYC and compliance automation pipelines with spaCy/NLTK.