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

I'm Pavan Ganeshreddy Yeruva, an Applied AI / Machine Learning Engineer with 4+ years of experience designing and owning production-grade ML and LLM systems in financial services and healthcare environments. I specialize in Retrieval-Augmented Generation (RAG), real-time NLP systems, scalable data pipelines, and explainable AI in regulated domains. I am open to relocating from New Jersey to pursue impactful enterprise AI initiatives. I've delivered systems processing 10TB+ of data monthly and serving 15,000+ internal users weekly, built end-to-end ML pipelines with automated retraining and governance, and implemented explainability frameworks across finance models to strengthen regulatory transparency. I collaborate with compliance, data engineering, and business stakeholders to align AI outputs with KPIs, risk controls, and operational objectives, while maintaining robust CI/CD deployment and monitoring in AWS.…I'm Pavan Ganeshreddy Yeruva, an Applied AI / Machine Learning Engineer with 4+ years of experience designing and owning production-grade ML and LLM systems in financial services and healthcare environments. I specialize in Retrieval-Augmented Generation (RAG), real-time NLP systems, scalable data pipelines, and explainable AI in regulated domains. I am open to relocating from New Jersey to pursue impactful enterprise AI initiatives. I've delivered systems processing 10TB+ of data monthly and serving 15,000+ internal users weekly, built end-to-end ML pipelines with automated retraining and governance, and implemented explainability frameworks across finance models to strengthen regulatory transparency. I collaborate with compliance, data engineering, and business stakeholders to align AI outputs with KPIs, risk controls, and operational objectives, while maintaining robust CI/CD deployment and monitoring in AWS.

Pavan Ganeshreddy Yeruva

Data Scientist, AI Engineer, AI Developer, +2





I'm Pavan Ganeshreddy Yeruva, an Applied AI / Machine Learning Engineer with 4+ years of experience designing and owning production-grade ML and LLM systems in financial services and healthcare environments. I specialize in Retrieval-Augmented Generation (RAG), real-time NLP systems, scalable data pipelines, and explainable AI in regulated domains. I am open to relocating from New Jersey to pursue impactful enterprise AI initiatives. I've delivered systems processing 10TB+ of data monthly and serving 15,000+ internal users weekly, built end-to-end ML pipelines with automated retraining and governance, and implemented explainability frameworks across finance models to strengthen regulatory transparency. I collaborate with compliance, data engineering, and business stakeholders to align AI outputs with KPIs, risk controls, and operational objectives, while maintaining robust CI/CD deployment and monitoring in AWS.…I'm Pavan Ganeshreddy Yeruva, an Applied AI / Machine Learning Engineer with 4+ years of experience designing and owning production-grade ML and LLM systems in financial services and healthcare environments. I specialize in Retrieval-Augmented Generation (RAG), real-time NLP systems, scalable data pipelines, and explainable AI in regulated domains. I am open to relocating from New Jersey to pursue impactful enterprise AI initiatives. I've delivered systems processing 10TB+ of data monthly and serving 15,000+ internal users weekly, built end-to-end ML pipelines with automated retraining and governance, and implemented explainability frameworks across finance models to strengthen regulatory transparency. I collaborate with compliance, data engineering, and business stakeholders to align AI outputs with KPIs, risk controls, and operational objectives, while maintaining robust CI/CD deployment and monitoring in AWS.

Available to hire

I’m Pavan Ganeshreddy Yeruva, an Applied AI / Machine Learning Engineer with 4+ years of experience designing and owning production-grade ML and LLM systems in financial services and healthcare environments. I specialize in Retrieval-Augmented Generation (RAG), real-time NLP systems, scalable data pipelines, and explainable AI in regulated domains. I am open to relocating from New Jersey to pursue impactful enterprise AI initiatives.

I’ve delivered systems processing 10TB+ of data monthly and serving 15,000+ internal users weekly, built end-to-end ML pipelines with automated retraining and governance, and implemented explainability frameworks across finance models to strengthen regulatory transparency. I collaborate with compliance, data engineering, and business stakeholders to align AI outputs with KPIs, risk controls, and operational objectives, while maintaining robust CI/CD deployment and monitoring in AWS.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

AI/ML Engineer at American Express

September 1, 2024 - Present

Architected and led development of a real-time enterprise NLP assistant leveraging RAG (LangChain + LLaMA + Pinecone) to support 15,000+ weekly internal queries, reducing average support resolution time by approximately 60–70% and lowering analyst backlog. Designed hybrid retrieval strategies and evaluated chunking, embedding models, and prompt configurations to improve answer relevance while minimizing hallucination risk. Built and scaled an internal knowledge platform indexing 500+ enterprise documents, improving cross-functional knowledge access. Engineered end-to-end ML pipelines processing 10TB+ of structured and unstructured data monthly with automated retraining triggers, experiment tracking, validation checks, and version governance. Developed predictive risk and operational models (PyTorch, XGBoost), implemented explainability (SHAP, LIME), and operationalized a real-time event-driven risk scoring pipeline using Kafka and Spark Structured Streaming. Established production de

Machine Learning Scientist at HCL Tech

January 1, 2021 - August 1, 2023

Led development of patient risk prediction models (LSTM, XGBoost) trained on 2.1M+ anonymized clinical records; built real-time clinical NLP pipelines processing 10,900+ physician notes weekly; developed CNN-based medical image classification models on 37,000+ diagnostic images; orchestrated scalable healthcare data pipelines handling 3TB+ EHR/claims data monthly; created privacy-preserving synthetic data generation workflows; standardized ML lifecycle practices with MLflow, model versioning, and CI/CD; translated analytical outputs into operational dashboards and measurable healthcare indicators.