About
I’m a Machine Learning Engineer specializing in LLMs, RAG systems, agentic AI, and production-grade ML pipelines. I build AI systems end-to-end from data to models, deployment, monitoring, and optimization with a focus on reliability, scalability, and real business impact. I’ve deployed ML and GenAI systems across telecom and enterprise environments, including production RAG pipelines, AI agents, real-time anomaly detection systems, and cloud-native ML platforms. Recently, I built RAG and agentic AI systems that processed 50K+ monthly queries, improved retrieval accuracy to 92%, and reduced manual intervention by 45%. My work includes: LLM/RAG pipelines, agentic AI assistants, hybrid retrieval MLOps with MLflow, SageMaker, Docker, Kubernetes, and CI/CD Distributed data engineering with Spark, Kafka, and Airflow Forecasting and anomaly detection for large-scale systems I also bring a background in blockchain innovation, having patented a blockchain-enabled idea-collaboration platform. That experience shaped how I think about trust, security, and distributed system design principles I now apply to scalable AI systems. I’m looking for roles where I can build and scale LLM/GenAI applications, design end-to-end ML architectures on cloud, and work closely with engineering and product teams to deliver reliable, user-focused AI. If your team is building AI that is scalable, dependable, and meaningful, I’d love to connect.
Work experience
Machine Learning Engineer at Verizon, Aug 2024 - Present · 2 yrs 1 mo
Graduate Teaching Assistant at University of North Texas, Jan 2024 - Jul 2024 · 7 mos
AI/ML Engineer at Wipro, Feb 2022 - Aug 2023 · 1 yr 7 mos
