G Kiran

About G Kiran

Generative AI Engineer with 9+ years of experience building intelligent AI applications using LLMs, NLP, and Machine Learning. Experienced in developing RAG pipelines, prompt engineering, and AI-powered automation solutions using technologies like OpenAI, LangChain, Hugging Face, and vector databases.Skilled in Python, TensorFlow, PyTorch, and cloud platforms (AWS, Azure, GCP) with strong experience deploying scalable AI systems and integrating models into enterprise applications. Passionate about building next-generation AI solutions that transform data into intelligent, real-world applications.

Experience

1. Gen Ai Engineer

   Johnson & Johnson

   Apr 2025 — Present · New Brunswick, NJ, US

   Working as a Generative AI Engineer, I design and develop AI-driven applications using Large Language Models (LLMs) to solve complex business problems. My work primarily focuses on building Retrieval-Augmented Generation (RAG) solutions by integrating enterprise data with LLMs to generate accurate and context-aware responses. I develop end-to-end pipelines including data preprocessing, embeddings, and vector search using tools like Python, LangChain, and Hugging Face. I also build and deploy scalable APIs and microservices, leveraging cloud platforms such as AWS and Azure along with Docker and Kubernetes. Additionally, I work on prompt engineering, model optimization, and performance monitoring to improve accuracy, reduce latency, and ensure reliable AI solutions in production environments.

Education

• Sacred Heart University

  Master's degree