I am a Generative AI Engineer with more than 10 years of experience building production-grade AI and machine learning systems across healthcare, enterprise, telecom, and manufacturing domains. My background spans LLM engineering, agentic AI, retrieval-augmented generation, transformer fine-tuning, and cloud-native AI platforms.
I have designed autonomous AI agents using LangChain, LangGraph, and MCP, and integrated OpenAI models to support multi-step reasoning, tool orchestration, and enterprise automation. I have also built and optimized RAG systems with FAISS, Pinecone, Chroma, and Weaviate to improve semantic search, knowledge management, and workflow automation.
My work includes fine-tuning GPT, LLaMA, T5, and BERT models with LoRA and QLoRA, as well as applying quantization, pruning, knowledge distillation, and prompt engineering to improve model accuracy and efficiency. I have developed end-to-end ML and LLM pipelines covering ingestion, training, deployment, monitoring, and real-time processing.
I have strong experience in MLOps and LLMOps, using tools such as MLflow, LangSmith, Kubeflow, Databricks, and Weights & Biases for experiment tracking, model versioning, retraining, and production monitoring. I have also deployed AI solutions across AWS, Azure, and GCP using Docker, Kubernetes, Terraform, and Helm.
In my recent roles, I have built secure and compliant GenAI services for healthcare and enterprise use cases, including document intelligence, code generation copilots, and internal knowledge retrieval systems. I have worked closely with cross-functional teams to deliver scalable APIs, improve developer productivity, and reduce manual effort in critical workflows.
Earlier in my career, I developed machine learning, NLP, forecasting, recommendation, and anomaly detection solutions for customer servicing, telecom analytics, manufacturing optimization, and data science automation. I bring a strong combination of technical depth, platform engineering, and applied AI delivery experience.
