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

AI/ML Engineer with 10+ years of experience designing, developing, and deploying enterprise-scale AI/ML and Generative AI solutions across Healthcare, Banking, and Technology. Expertise spans LLM-based applications, Retrieval-Augmented Generation (RAG), AI agents/multi-agent systems, and production-grade orchestration frameworks such as LangGraph, Semantic Kernel, and AutoGen. Strong software engineering background with expert Python and cloud-native microservices/MLOps experience on AWS, Azure, and GCP. Proven success delivering end-to-end AI platforms: data ingestion, embeddings and vector search, prompt engineering, evaluation, deployment, monitoring, governance, and optimization—plus building safe, compliant, and observable AI systems for real-world enterprise workflows.…AI/ML Engineer with 10+ years of experience designing, developing, and deploying enterprise-scale AI/ML and Generative AI solutions across Healthcare, Banking, and Technology. Expertise spans LLM-based applications, Retrieval-Augmented Generation (RAG), AI agents/multi-agent systems, and production-grade orchestration frameworks such as LangGraph, Semantic Kernel, and AutoGen. Strong software engineering background with expert Python and cloud-native microservices/MLOps experience on AWS, Azure, and GCP. Proven success delivering end-to-end AI platforms: data ingestion, embeddings and vector search, prompt engineering, evaluation, deployment, monitoring, governance, and optimization—plus building safe, compliant, and observable AI systems for real-world enterprise workflows.

Daedeepya

AI Engineer, Data Scientist, AI Developer, +3





AI/ML Engineer with 10+ years of experience designing, developing, and deploying enterprise-scale AI/ML and Generative AI solutions across Healthcare, Banking, and Technology. Expertise spans LLM-based applications, Retrieval-Augmented Generation (RAG), AI agents/multi-agent systems, and production-grade orchestration frameworks such as LangGraph, Semantic Kernel, and AutoGen. Strong software engineering background with expert Python and cloud-native microservices/MLOps experience on AWS, Azure, and GCP. Proven success delivering end-to-end AI platforms: data ingestion, embeddings and vector search, prompt engineering, evaluation, deployment, monitoring, governance, and optimization—plus building safe, compliant, and observable AI systems for real-world enterprise workflows.…AI/ML Engineer with 10+ years of experience designing, developing, and deploying enterprise-scale AI/ML and Generative AI solutions across Healthcare, Banking, and Technology. Expertise spans LLM-based applications, Retrieval-Augmented Generation (RAG), AI agents/multi-agent systems, and production-grade orchestration frameworks such as LangGraph, Semantic Kernel, and AutoGen. Strong software engineering background with expert Python and cloud-native microservices/MLOps experience on AWS, Azure, and GCP. Proven success delivering end-to-end AI platforms: data ingestion, embeddings and vector search, prompt engineering, evaluation, deployment, monitoring, governance, and optimization—plus building safe, compliant, and observable AI systems for real-world enterprise workflows.

Available to hire

AI/ML Engineer with 10+ years of experience designing, developing, and deploying enterprise-scale AI/ML and Generative AI solutions across Healthcare, Banking, and Technology. Expertise spans LLM-based applications, Retrieval-Augmented Generation (RAG), AI agents/multi-agent systems, and production-grade orchestration frameworks such as LangGraph, Semantic Kernel, and AutoGen.

Strong software engineering background with expert Python and cloud-native microservices/MLOps experience on AWS, Azure, and GCP. Proven success delivering end-to-end AI platforms: data ingestion, embeddings and vector search, prompt engineering, evaluation, deployment, monitoring, governance, and optimization—plus building safe, compliant, and observable AI systems for real-world enterprise workflows.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Work Experience

AI Agent Engineer at Cardinal Health

January 1, 2024 - Present

Architected and deployed enterprise-grade AI agent platforms using LangGraph and GPT-4 to automate clinical documentation, claims analysis, and healthcare workflow orchestration. Built clinical knowledge assistants using GPT-4 with RAG architectures, and designed multi-agent systems for autonomous reasoning, task planning, tool selection, and decision execution. Implemented AI governance frameworks for safety, observability, compliance, monitoring, and model evaluation. Built reusable agent frameworks supporting tool integration, workflow orchestration, memory management, and autonomous execution, while optimizing latency, throughput, token consumption, and operational cost. Developed CI/CD pipelines for LLM deployment, evaluation, and production monitoring. Created advanced RAG pipelines leveraging Pinecone and OpenAI embeddings with hybrid retrieval to improve response accuracy, and integrated assistants with EHR systems, healthcare APIs, and regulatory repositories. Ensured HIPAA-co

AI Agent Engineer (Senior AI/ML Engineer) at Cardinal Health

January 1, 2024 - Present

Architected and deployed enterprise-grade AI agent platforms using LangGraph and GPT-4 to automate clinical documentation, claims analysis, and healthcare workflow orchestration. Built clinical knowledge assistants using GPT-4 with RAG architectures and designed multi-agent systems for autonomous reasoning, task planning, tool selection, and decision execution across healthcare business processes. Implemented AI governance frameworks covering safety, observability, compliance, monitoring, and model evaluation; built reusable agent frameworks for tool integration, workflow orchestration, memory management, and autonomous execution. Optimized latency, throughput, token usage, and operational costs. Implemented CI/CD pipelines for LLM deployment, evaluation, and production monitoring. Developed advanced RAG pipelines using Pinecone with hybrid retrieval strategies to improve response accuracy, and integrated agents with EHR systems, healthcare APIs, and regulatory documentation repositori

Senior AI/ML Engineer at Nationwide

March 1, 2022 - December 31, 2023

Developed HIPAA-compliant AI workflows with safety guardrails and retrieval grounding. Built intelligent healthcare/member support assistants using GPT-4 and Claude for benefit explanation and provider search workflows. Designed hybrid retrieval systems combining vector search, keyword search, metadata filtering, and reranking models. Implemented semantic search and RAG pipelines using ChromaDB and FAISS; fine-tuned and optimized LLM performance through prompt optimization, retrieval augmentation, and model evaluation with feedback-driven improvements. Designed autonomous AI agents integrating internal APIs, EMR systems, and healthcare databases. Built model evaluation pipelines to track relevance, latency, safety, and cost metrics and collaborated with product, compliance, and clinical teams for regulatory alignment and responsible AI deployment. Implemented scalable data pipelines using Databricks, Snowflake, Spark, and Delta Lake for ingestion, transformation, and feature engineerin

AI/ML Engineer at Molina Health

March 1, 2020 - February 28, 2022

Translated customer requirements into software design specifications. Built multi-agent systems supporting task planning, tool execution, and validation workflows. Developed NLP and machine learning solutions for clinical document classification, patient risk stratification, and predictive analytics. Implemented token optimization and caching strategies to reduce inference costs and improve response latency. Built recommendation systems to improve user engagement and enterprise search relevance. Designed data ingestion pipelines for large-scale healthcare datasets and automated clinical workflow processes using machine learning and conversational AI. Worked primarily on AI/ML solutions in Python using TensorFlow/PyTorch/Scikit-Learn and Spark with AWS.

Senior Machine Learning Engineer at BMO Harris Bank

January 1, 2016 - May 31, 2019

Built AI-powered fraud detection and financial risk analysis systems using machine learning and deep learning methods. Developed agent memory and tool-calling capabilities integrating enterprise APIs and databases. Implemented agent evaluation frameworks measuring accuracy, safety, and task completion rates. Reduced inference latency using caching and prompt optimization. Designed intelligent document processing pipelines for loan and compliance documentation. Established end-to-end MLOps pipelines for automated training, validation, deployment, monitoring, rollback, and lifecycle management. Built citation-enabled response systems for transparency and traceability and developed conversational banking assistants using NLP and transformer-based architectures. Implemented ML deployment and lifecycle management with AWS and Kubernetes.

Machine Learning Engineer at Data Factz

August 1, 2014 - June 30, 2015

Improved retrieval accuracy using hybrid search and reranking strategies. Built predictive analytics and customer segmentation models for enterprise clients, including classification, forecasting, and anomaly detection pipelines. Developed REST APIs exposing machine learning models for enterprise consumption. Worked with stakeholder requirements translation into AI-driven solutions. Built data/ML pipelines using Python with Flask, Scikit-Learn, Pandas, NumPy, and SQL Server deployed in AWS environments.