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

Senior Generative AI & LLM engineer with 6+ years of experience building enterprise-grade RAG systems, LLM-powered assistants, and agentic AI workflows using OpenAI/Azure OpenAI, LangChain/LangGraph, Semantic Kernel, and vector databases. Skilled in LLM orchestration, retrieval pipelines, evaluation/safety, and multi-agent tool-using systems for automated insights and workflow automation. Architects scalable MLOps platforms with MLflow, FastAPI, Docker, and Kubernetes, delivering secure and compliant LLM deployments aligned with HIPAA/GDPR. Has delivered measurable impact across finance and healthcare, including faster knowledge retrieval, reduced documentation effort, and improved reliability through drift-aware retraining and governance.…Senior Generative AI & LLM engineer with 6+ years of experience building enterprise-grade RAG systems, LLM-powered assistants, and agentic AI workflows using OpenAI/Azure OpenAI, LangChain/LangGraph, Semantic Kernel, and vector databases. Skilled in LLM orchestration, retrieval pipelines, evaluation/safety, and multi-agent tool-using systems for automated insights and workflow automation. Architects scalable MLOps platforms with MLflow, FastAPI, Docker, and Kubernetes, delivering secure and compliant LLM deployments aligned with HIPAA/GDPR. Has delivered measurable impact across finance and healthcare, including faster knowledge retrieval, reduced documentation effort, and improved reliability through drift-aware retraining and governance.

Bhargavi T

AI Engineer, Data Scientist, Data Analyst, +2





Senior Generative AI & LLM engineer with 6+ years of experience building enterprise-grade RAG systems, LLM-powered assistants, and agentic AI workflows using OpenAI/Azure OpenAI, LangChain/LangGraph, Semantic Kernel, and vector databases. Skilled in LLM orchestration, retrieval pipelines, evaluation/safety, and multi-agent tool-using systems for automated insights and workflow automation. Architects scalable MLOps platforms with MLflow, FastAPI, Docker, and Kubernetes, delivering secure and compliant LLM deployments aligned with HIPAA/GDPR. Has delivered measurable impact across finance and healthcare, including faster knowledge retrieval, reduced documentation effort, and improved reliability through drift-aware retraining and governance.…Senior Generative AI & LLM engineer with 6+ years of experience building enterprise-grade RAG systems, LLM-powered assistants, and agentic AI workflows using OpenAI/Azure OpenAI, LangChain/LangGraph, Semantic Kernel, and vector databases. Skilled in LLM orchestration, retrieval pipelines, evaluation/safety, and multi-agent tool-using systems for automated insights and workflow automation. Architects scalable MLOps platforms with MLflow, FastAPI, Docker, and Kubernetes, delivering secure and compliant LLM deployments aligned with HIPAA/GDPR. Has delivered measurable impact across finance and healthcare, including faster knowledge retrieval, reduced documentation effort, and improved reliability through drift-aware retraining and governance.

Available to hire

Senior Generative AI & LLM engineer with 6+ years of experience building enterprise-grade RAG systems, LLM-powered assistants, and agentic AI workflows using OpenAI/Azure OpenAI, LangChain/LangGraph, Semantic Kernel, and vector databases. Skilled in LLM orchestration, retrieval pipelines, evaluation/safety, and multi-agent tool-using systems for automated insights and workflow automation.

Architects scalable MLOps platforms with MLflow, FastAPI, Docker, and Kubernetes, delivering secure and compliant LLM deployments aligned with HIPAA/GDPR. Has delivered measurable impact across finance and healthcare, including faster knowledge retrieval, reduced documentation effort, and improved reliability through drift-aware retraining and governance.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Work Experience

Senior AI/ML Engineer | GenAI & MLOps Engineer | Multi-Cloud Architect at Northern Trust

April 1, 2025 - Present

Architected a unified multi-cloud GenAI platform and enterprise RAG pipelines using LangChain, FAISS, GPT-4/Gemini, and hybrid retrieval strategies, achieving ~3x faster knowledge retrieval. Built agentic AI assistants using LangGraph/Semantic Kernel for reasoning, task decomposition, tool use, structured extraction, and self-correcting workflows to automate analytical tasks in finance/operations/risk. Developed LLM summarization/financial Q&A systems that reduced manual analyst effort by ~45%. Implemented LLM evaluation and safety frameworks (toxicity filters, factuality checks, prompt hardening, behavioral tests). Delivered drift-aware retraining pipelines with MLflow and Python automation, and deployed hardened RAG/GenAI APIs using FastAPI + Kubernetes + Azure Functions with RBAC, VNET isolation, TLS, Key Vault/Secrets Manager, and audit logging.

Senior AI/ML Engineer at Northern Trust

April 1, 2025 - Present

Architected a unified multi-cloud GenAI platform using Python, OpenAI/Azure OpenAI, AWS Lambda, and GCP Vertex AI to standardize LLM deployment, evaluation, and governance, reducing AI rollout time by 40% across business units. Designed and deployed enterprise RAG pipelines with LangChain, FAISS, GPT-4/Gemini, and custom embeddings, delivering ~3x faster knowledge retrieval. Built agentic AI assistants with LangGraph and Semantic Kernel to automate complex analytical tasks in finance, operations, and risk. Developed LLM-powered summarization and Q&A systems to cut manual analyst effort by ~45% and accelerate reporting. Implemented drift-aware retraining pipelines (MLflow, ADF, Lambda) for automated model refresh and drift alerts. Deployed secure GenAI & RAG APIs (FastAPI, Kubernetes, Azure Functions) with RBAC, VNET isolation, TLS, Key Vault, and audit logging. Reduced LLM retrieval latency by 70% with advanced embeddings and Databricks/Spark optimizations. Collaborated with product, a

AI/ML Engineer | Generative AI & MLOps Engineer at Molina Healthcare

May 1, 2023 - March 31, 2025

Delivered clinical-grade GenAI systems improving documentation, triage, coding, and physician efficiency. Built HIPAA-compliant Clinical GenAI Assistant using Python, Azure OpenAI, LangChain, and RAG pipelines to automate FAQs, triage support, prescription workflows, and prior authorization queries—reducing provider support workload by ~40%. Productionized LLM-based summarization and clinical documentation automation, enabling structured SOAP notes and chart updates, cutting documentation time by 35–45%. Engineered RAG pipelines retrieving context from EHRs, labs, radiology reports, guidelines, claims, and patient histories (FAISS/Pinecone) for 5x faster access to clinical facts. Fine-tuned GPT-4, LLaMA2, BERT, and T5 for medical NER, ICD/CPT code suggestion, clinical Q&A, and risk classification. Developed real-time clinical decision support APIs (FastAPI + Kubernetes + MLflow). Implemented LLM evaluation, safety controls, and drift-aware retraining. Integrated OCR (OpenCV/Tessera

Data Scientist | Cloud Data Pipelines | Spark & AWS | Early MLOps Contributor at Wipro

July 1, 2019 - July 1, 2022

Designed and optimized Python + PySpark pipelines in Databricks to transform raw enterprise data into ML-ready feature datasets for forecasting, segmentation, and risk analytics. Built metadata-driven ingestion frameworks using AWS Glue, Lambda, and Step Functions to automate hundreds of batch workflows and reduce manual orchestration overhead by ~80%. Improved ML preprocessing performance by ~50% through Spark query tuning and Delta file layout optimizations. Implemented data quality validation layers to catch schema anomalies and integrity issues early. Created CI/CD pipelines for deploying ETL/data-prep modules (Git, AWS CodePipeline, CodeBuild) and added SLA/performance monitoring dashboards using CloudWatch & QuickSight to reduce incident response times. Contributed to Lakehouse/medallion initiatives aligned to feature accessibility and reduced training delays.

Data Scientist | Cloud Data Pipelines | Spark & AWS | Early MLOps Contributor at Wipro India

July 1, 2019 - July 1, 2022

Built AI-ready data platforms and automated pipelines supporting ML and analytics across large enterprises. Designed and optimized Python + PySpark pipelines in Databricks to create ML-ready feature datasets. Developed metadata-driven ingestion frameworks using AWS Glue, Lambda, and Step Functions, automating hundreds of batch workflows and reducing orchestration overhead by ~80%. Enhanced ML preprocessing performance via Spark optimizations. Created high-quality feature engineering modules and data quality validation layers. Implemented CI/CD pipelines for ML data flows and built SLA dashboards (CloudWatch & QuickSight) to monitor latency and throughput. Collaborated to define data contracts and feature consumption patterns, contributing to Lakehouse medallion architecture.

Intern Software Engineer | Data Engineering & Cloud Migration at APTOnline

January 1, 2019 - June 1, 2019

Assisted in migrating on-prem datasets to Azure Data Lake and AWS S3 to improve scalability and accessibility for analytics/ML teams. Developed Python-based ETL scripts for cleaning, validation, and transformation to improve dataset quality for reporting and experiments. Supported creation of ADF and AWS Glue ingestion pipelines to automate batch workflows and reduce manual refresh cycles. Implemented basic feature preprocessing routines (filtering, encoding, deduplication) for ML pilot prep and optimized early Spark jobs using partitioning and caching. Built lightweight automation utilities in Python and Bash for repetitive operational tasks.

Intern Software Engineer | Data Engineering & Cloud Migration at APTOnline India

January 1, 2019 - June 1, 2019

Contributed to cloud migration and AI-ready data preparation pipelines for analytics and ML pilots. Assisted in migrating on-prem datasets to Azure Data Lake and AWS S3, enabling scalable storage for analytics/ML teams. Developed Python-based ETL scripts for data cleaning, validation, and transformation. Supported creation of ADF and AWS Glue ingestion pipelines, automating batch workflows. Implemented basic feature preprocessing routines and optimized early Spark jobs. Built lightweight automation utilities to assist engineering teams with repetitive tasks.