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

Senior Generative AI/ML Engineer with 10+ years of experience building and deploying enterprise-grade AI/ML and Generative AI solutions across Finance, Healthcare, Insurance, Retail, and Technology. Strong expertise in LLM engineering (RAG, agentic/multi-agent systems, prompt engineering), evaluation/observability, and production LLMOps/MLOps for reliable, secure outcomes. Hands-on across AWS, Azure, and GCP—designing scalable AI platform architectures, vector search and hybrid retrieval, and high-performance AI microservices. Proven ability to reduce costs and latency, improve retrieval and answer quality, and deliver business automation through secure integrations and responsible AI practices.…Senior Generative AI/ML Engineer with 10+ years of experience building and deploying enterprise-grade AI/ML and Generative AI solutions across Finance, Healthcare, Insurance, Retail, and Technology. Strong expertise in LLM engineering (RAG, agentic/multi-agent systems, prompt engineering), evaluation/observability, and production LLMOps/MLOps for reliable, secure outcomes. Hands-on across AWS, Azure, and GCP—designing scalable AI platform architectures, vector search and hybrid retrieval, and high-performance AI microservices. Proven ability to reduce costs and latency, improve retrieval and answer quality, and deliver business automation through secure integrations and responsible AI practices.

Lakshmi Bhargavi

AI Engineer, Data Scientist, Web Developer, +2





Senior Generative AI/ML Engineer with 10+ years of experience building and deploying enterprise-grade AI/ML and Generative AI solutions across Finance, Healthcare, Insurance, Retail, and Technology. Strong expertise in LLM engineering (RAG, agentic/multi-agent systems, prompt engineering), evaluation/observability, and production LLMOps/MLOps for reliable, secure outcomes. Hands-on across AWS, Azure, and GCP—designing scalable AI platform architectures, vector search and hybrid retrieval, and high-performance AI microservices. Proven ability to reduce costs and latency, improve retrieval and answer quality, and deliver business automation through secure integrations and responsible AI practices.…Senior Generative AI/ML Engineer with 10+ years of experience building and deploying enterprise-grade AI/ML and Generative AI solutions across Finance, Healthcare, Insurance, Retail, and Technology. Strong expertise in LLM engineering (RAG, agentic/multi-agent systems, prompt engineering), evaluation/observability, and production LLMOps/MLOps for reliable, secure outcomes. Hands-on across AWS, Azure, and GCP—designing scalable AI platform architectures, vector search and hybrid retrieval, and high-performance AI microservices. Proven ability to reduce costs and latency, improve retrieval and answer quality, and deliver business automation through secure integrations and responsible AI practices.

Available to hire

Senior Generative AI/ML Engineer with 10+ years of experience building and deploying enterprise-grade AI/ML and Generative AI solutions across Finance, Healthcare, Insurance, Retail, and Technology. Strong expertise in LLM engineering (RAG, agentic/multi-agent systems, prompt engineering), evaluation/observability, and production LLMOps/MLOps for reliable, secure outcomes.

Hands-on across AWS, Azure, and GCP—designing scalable AI platform architectures, vector search and hybrid retrieval, and high-performance AI microservices. Proven ability to reduce costs and latency, improve retrieval and answer quality, and deliver business automation through secure integrations and responsible AI practices.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Advanced

Work Experience

Senior Generative AI/ML Engineer at Corpay

June 1, 2024 - Present

Designed and implemented multi-agent AI systems for financial audit workflows using LangGraph and CrewAI. Built MCP-enabled AI services to integrate enterprise knowledge with LLM applications and implemented hybrid retrieval (BM25 + vector search) to improve document search accuracy and reduce hallucinations. Developed reusable AI microservices using FastAPI and Kubernetes, optimizing token usage and inference costs (reduced OpenAI spend by 30%). Implemented automated LLM evaluation pipelines using RAGAS/DeepEval/LangSmith and added AI guardrails such as prompt-injection detection, jailbreak prevention, output filtering, and sensitive data protection. Built event-driven AI workflows using Kafka and integrated multi-model orchestration across Amazon Bedrock and Azure OpenAI. Engineered enterprise-scale RAG over 5M documents (improved retrieval time by 65% and answer accuracy by 42%) with LLM observability via LangSmith and Arize Phoenix. Supported ML forecasting models on AWS SageMaker

Generative AI/ML Engineer at CareFirst BlueCross BlueShield

March 1, 2022 - June 1, 2024

Built end-to-end ML pipelines for clinical note extraction and summarization using TensorFlow/PyTorch with MLflow for model tracking. Deployed transformer-based NLP models to production using Docker/Kubernetes and REST APIs (Flask/FastAPI). Implemented real-time and batch inference pipelines using Kafka, Spark, and Airflow to deliver insights with low latency. Fine-tuned domain-specific LLMs (GPT-4, LLaMA, Falcon) for summarization, Q&A, and retrieval over medical records and research. Developed healthcare agentic assistants to autonomously retrieve patient data and generate clinical summaries, and built multimodal solutions combining images, notes, and structured data using GPT-4o/Gemini. Implemented HIPAA-compliant LLMOps with evaluation, monitoring, and governance, plus RAG evaluation using RAGAS/LangSmith/OpenAI Evals. Added explainability using SHAP/LIME, deployed monitoring with Prometheus, and created dashboards using Streamlit/Dash/Power BI. Integrated clinical AI pipelines wit

Data Scientist at UPS

August 1, 2018 - June 1, 2021

Developed deep learning models for fraud detection (image classification), claims summarization (NLP), and transaction forecasting (time series). Built CNNs for document/ID verification and modeled customer financial events/support interactions using LSTMs and Transformers. Deployed transformer models (BERT/GPT-2/T5) for sentiment analysis, NER, and summarization via Docker to SageMaker and other cloud platforms with scalable inference on Kubernetes. Integrated LLM APIs (OpenAI/Cohere/Anthropic) for automated document summarization, intent detection, and support responses. Created full-stack ML workflows including ingestion/cleaning/feature engineering, training, serving, and drift monitoring. Built analyst-friendly tools in Streamlit/Gradio for running churn models, automated hyperparameter tuning, and implemented recommendation/ranking using XGBoost and clickstream data. Used SHAP/LIME/ELI5 for explainability and bias/fairness monitoring. Implemented CI/CD with Airflow/MLflow/Docker/

Data Scientist at Macy's

September 1, 2015 - July 1, 2018

Built automated data pipelines in Python/SQL using Airflow for ingestion, transformation, and reporting. Conducted EDA to find trends, anomalies, and actionable insights. Developed supervised and unsupervised ML models for segmentation and churn prediction, and applied NLP to millions of customer reviews (sentiment, NER, topic modeling). Fine-tuned deep learning for text/image classification, and built production recommendation systems using collaborative filtering and content-based methods. Packaged and served models using Flask/FastAPI, Docker, and Kubernetes for low-latency inference. Implemented experiment tracking with MLflow/DVC/W&B, and set up monitoring with Prometheus/Grafana for drift and performance. Built end-to-end pipelines with TensorFlow Serving and automated CI/CD with Docker/Kubernetes for testing, deployment, and rollback.