Chaitanya Yadlapalli

About Chaitanya Yadlapalli

I am a Lead AI/ML Engineer specialized in architecting and productionizing enterprise-grade Generative AI ecosystems and GCP Cloud infrastructures. My core expertise lies in the design of sophisticated Agentic AI workflows and scalable RAG pipelines utilizing LangChain, LangGraph, and Vertex AI. I excel at translating intricate business requirements into high-performance AI solutions that facilitate automation, substantial cost optimization, and enhanced decision-making within the healthcare and life sciences domains.My technical methodology emphasizes the full MLOps lifecycle, from rigorous experimentation and RLHF implementation to the deployment of low-latency FastAPI microservices. I possess a deep proficiency in integrating Large Language Models with complex data environments through BigQuery, Databricks, and vector databases like Pinecone and FAISS. By establishing production-grade deployment patterns—including autoscaling, caching, and real-time observability—I ensure that AI applications are not only powerful but also resilient and operationally sound.Beyond architecture, I am committed to Responsible AI and rigorous governance. I lead cross-functional collaborations with compliance and clinical teams to harden systems against hallucinations and ensure strict adherence to HIPAA and PHI data privacy standards. As a technical mentor, I contribute to the open-source community by developing frameworks for retrieval optimization and automated evaluation, constantly pushing the boundaries of what is possible in modern NLP and LLM engineering.

Experience

1. Lead Gen Ai Engineer

   Hsbcbank-Usa

   Feb 2024 — Present

   Leading the design and production deployment of enterprise-scale Generative AI and LLM platforms across regulated financial and healthcare domains. Architected end-to-end ML and GenAI infrastructure on AWS, enabling rapid development, training, and deployment of scalable LLM solutions using SageMaker, Lambda, API Gateway, and containerized microservices. Built robust multimodal AI pipelines integrating text, image, and audio embeddings to enhance document understanding, real-time assistance, and internal R&D workflows.Specialized in productionizing LLMs through advanced RAG architectures, hybrid retrieval strategies, RLHF optimization, and rigorous evaluation frameworks using PyTorch, Hugging Face, and MLflow. Optimized data and training pipelines using Databricks Lakehouse, significantly reducing ETL and model training latency. Established production-grade GenAI deployment patterns with autoscaling, monitoring, caching, guardrails, and governance aligned with HIPAA, PHI, and enterprise compliance standards.Collaborate closely with product, security, legal, and compliance teams to deliver safe, reliable, and cost-efficient AI solutions that drive measurable business impact, including improved decision accuracy and reduced operational costs. Actively contribute to open-source GenAI tooling and reusable RAG frameworks supporting enterprise AI adoption.

Education

• Wilmington University

  Information Systems

• SRM IST Chennai

  B.tech, Computer science engineering