I am an AI/ML engineer and data scientist with 8+ years of experience designing, building, and deploying scalable GenAI and traditional ML solutions across healthcare, financial services, and retail. I have hands-on experience with large language models (GPT-4, Claude, LLaMA), prompt engineering, retrieval-augmented generation (RAG), and enterprise LLM governance, delivered through robust cloud architectures and developer tooling. I thrive in cross-functional environments, turning complex data into production-ready AI features while championing responsible AI practices and explainability. I enjoy collaborating with product, compliance, and engineering teams to deliver measurable business value, accelerate AI adoption at scale, and improve data privacy, auditability, and governance. I’m passionate about reusable components, scalable architectures, and ongoing learning to push the boundaries of GenAI in regulated domains like healthcare and finance.

Sai Jahnavi Vemula

I am an AI/ML engineer and data scientist with 8+ years of experience designing, building, and deploying scalable GenAI and traditional ML solutions across healthcare, financial services, and retail. I have hands-on experience with large language models (GPT-4, Claude, LLaMA), prompt engineering, retrieval-augmented generation (RAG), and enterprise LLM governance, delivered through robust cloud architectures and developer tooling. I thrive in cross-functional environments, turning complex data into production-ready AI features while championing responsible AI practices and explainability. I enjoy collaborating with product, compliance, and engineering teams to deliver measurable business value, accelerate AI adoption at scale, and improve data privacy, auditability, and governance. I’m passionate about reusable components, scalable architectures, and ongoing learning to push the boundaries of GenAI in regulated domains like healthcare and finance.

Available to hire

I am an AI/ML engineer and data scientist with 8+ years of experience designing, building, and deploying scalable GenAI and traditional ML solutions across healthcare, financial services, and retail. I have hands-on experience with large language models (GPT-4, Claude, LLaMA), prompt engineering, retrieval-augmented generation (RAG), and enterprise LLM governance, delivered through robust cloud architectures and developer tooling. I thrive in cross-functional environments, turning complex data into production-ready AI features while championing responsible AI practices and explainability.

I enjoy collaborating with product, compliance, and engineering teams to deliver measurable business value, accelerate AI adoption at scale, and improve data privacy, auditability, and governance. I’m passionate about reusable components, scalable architectures, and ongoing learning to push the boundaries of GenAI in regulated domains like healthcare and finance.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
See more

Language

English
Fluent

Work Experience

Senior Gen AI / ML Engineer at Bayer HealthCare
June 1, 2023 - Present
Led the design and deployment of enterprise-grade GenAI applications for regulatory automation using large language models like GPT-4, Claude, and LLaMA. Developed advanced prompt engineering strategies and multi-agent AI workflows for document summarization, question answering, and regulatory validation. Built GenAI pipelines leveraging custom retrieval logic and dynamic chunking with vector databases such as Pinecone and FAISS. Implemented LLM microservices using AWS Lambda, API Gateway, and Bedrock. Applied OCR and image-based parsing for pharmacovigilance, collaborated on LLM governance to reduce hallucinations, and ensured compliance with healthcare data standards including FHIR, HL7, and HIPAA. Managed deployment workflows using AWS services and supported agile development alongside cross-functional teams.
Data Scientist / ML Engineer at North Trust Bank
May 31, 2023 - August 5, 2025
Designed and deployed LLM-powered solutions to automate insight extraction and summarization of unstructured financial documents supporting KYC/AML and fraud detection processes. Developed RAG pipelines with LangChain and FAISS to enable dynamic document search and enrichment, and deployed secure APIs with FastAPI and AWS Lambda for scalable GenAI application delivery. Built OCR-integrated document capture workflows using Amazon Textract and Azure Document Intelligence. Implemented auto-retraining ML pipelines triggered by data drift with Azure ML and MLflow. Developed predictive models improving underwriting accuracy and digital conversion rates. Mentored team members on responsible AI practices and prompt engineering methods. Delivered data visualization dashboards and performed statistical analysis to support compliance and fraud analytics.
Data Scientist at Genpact
June 1, 2020 - August 5, 2025
Developed end-to-end data science and ML solutions for retail and e-commerce clients including recommendation engines, customer segmentation, forecasting, and fraud detection models leveraging Python and XGBoost. Built containerized ML/NLP models with Docker, integrating services via REST APIs for real-time personalization and fraud systems. Employed NLP techniques on unstructured data for sentiment analysis and topic modeling. Conducted uplift modeling and A/B testing to optimize marketing campaigns, resulting in improved ROI and conversion rates. Created interactive dashboards using Tableau and Power BI for senior stakeholders. Explored early GenAI use cases for automating insight generation and document parsing in foundational stages.
Senior Gen AI / ML Engineer at Bayer HealthCare
June 1, 2023 - Present
Led design and deployment of enterprise GenAI applications for regulatory automation using LLMs (GPT-4, Claude, LLaMA). Built prompt engineering strategies, dynamic prompts, chunking and RAG pipelines with metadata filtering. Developed multi-agent AI systems (LangChain, LangGraph, and crewAI) for document summarization, Q&A, and regulatory validation. Implemented retrieval pipelines with Pinecone, FAISS, and Kendra; supervised tuning for improved retrieval. Deployed LLM microservices on AWS (Lambda, API Gateway, Bedrock) with real-time S3 triggers; applied OCR and image-based rule parsing with Textract. Collaborated on LLM governance, embedding similarity tuning, and relevance metrics (BLEU, ROUGE). Ensured cloud security, data lineage, and governance aligned with AWS Well-Architected Framework. Supported agile development with JIRA; coordinated with offshore teams; ensured HIPAA/FHIR compliance for healthcare data. Contributed to regulatory evaluations to reduce hallucination and impr
Data Scientist / ML Engineer at North Trust Bank
May 1, 2023 - September 5, 2025
Designed and deployed LLM-powered solutions to extract and summarize insights from unstructured financial documents, enhancing regulatory compliance and customer onboarding. Built prompt engineering and retrieval-augmented generation (RAG) pipelines with LangChain/FAISS for dynamic document search and LLM-context enrichment. Created secure API interfaces (FastAPI) to serve GenAI apps; deployed with AWS Lambda. Implemented NLP/GenAI models with Python, Docker, Kubernetes; established CI/CD with GitHub Actions/Jenkins. Built semantic search engines with FAISS; developed discrepancy detection and auto-retraining for data-drift. Integrated OCR-enabled document capture via Amazon Textract and Azure Document Intelligence. Led data exploration with PySpark, Snowflake, and SQL; delivered dashboards in Tableau/Power BI; mentored on responsible AI.
Data Scientist at Genpact
June 1, 2020 - September 5, 2025
Developed end-to-end data science solutions for retail and e-commerce, including recommendation engines, customer segmentation, and forecasting using Python, scikit-learn, and XGBoost. Built containerized ML/NLP models with Docker; performed NLP for reviews and sentiment analysis; conducted A/B testing and uplift modeling to improve campaigns. Created data pipelines (SQL/Python) for model training; delivered dashboards in Tableau/Power BI; implemented auto-retraining and feature scoring with SHAP. Drove fraud detection scoring and e-commerce personalization; supported GenAI exploration for automated insight generation from customer feedback and product reviews.
Senior Gen AI / ML Engineer at Bayer HealthCare
June 1, 2023 - Present
Led design and deployment of enterprise GenAI applications for regulatory automation using LLMs (GPT-4, Claude, LLaMA). Built multi-agent systems with LangChain, LangGraph, and crewAI for document summarization, Q&A, and regulatory validation. Implemented dynamic RAG pipelines with metadata filtering using Pinecone, FAISS, and Kendra; designed secure AWS/Azure architectures and evaluated SaaS/PaaS LLM providers for cost, performance, and compliance. Contributed to LLM governance, embedding similarity tuning, and hallucination reduction. Deployed LLM microservices on AWS using Lambda, API Gateway, and Bedrock; integrated OCR-based parsing with Textract; built MCP server for secure tool/data access; guided compliance with healthcare standards; led PoCs and cross-functional rollout.
Data Scientist / ML Engineer at North Trust Bank
May 1, 2023 - September 25, 2025
Designed and deployed LLM-powered solutions to extract and summarize insights from unstructured financial documents to support regulatory compliance and onboarding. Built prompt engineering frameworks for document Q&A, classification, and summarization; integrated RAG pipelines with LangChain/FAISS for dynamic document search; created secure FastAPI/AWS Lambda services; deployed NLP models with Docker/Kubernetes and CI/CD workflows. Built semantic search with FAISS, developed discrepancy detection modules, OCR document capture workflows, and end-to-end GenAI orchestration using S3/Lambda/Azure ML. Led auto-retraining triggers on data drift, mentored on responsible AI, and produced dashboards for management.
Data Scientist at Genpact
June 1, 2020 - September 25, 2025
Developed end-to-end data science solutions for retail and e-commerce, including recommendation engines, customer segmentation, and forecasting using Python, scikit-learn, and XGBoost. Built containerized ML/NLP models, performed topic modeling and sentiment analysis on unstructured data, conducted A/B testing and uplift modeling, and created data pipelines for multi-source data. Delivered dashboards and integrated ML services via REST APIs, enabling scalable, production-grade AI features.

Education

Bachelor of Engineering at SRM University, India
June 1, 2013 - May 1, 2017
Bachelor of Engineering at SRM University, India
June 1, 2013 - May 1, 2017
Bachelor of Engineering, Electrical at SRM University
June 1, 2013 - May 1, 2017

Qualifications

Add your qualifications or awards here.

Industry Experience

Healthcare, Financial Services, Retail, Life Sciences, Software & Internet