• Assisted in research and development team on Generative AI projects and developed solutions using open source LLMs and also analyzed capabilities of multiple LLM models, Stable diffusion models, and OpenAI models.• Optimized computational resources up to 70% for model training and implementation by using the capabilities of LoRA and QLoRA.• Developed solutions using large-scale models on constrained computational resources by leveraging distributed and parallel computing frameworks such as Ray, resulting in efficient workload distribution across multiple machines.• Worked on Generative AI models and its tools, RAG, LLM models, Prompt engineering, Fine-tuning, Parallel computing, Explainable AI, Web Scraping,LangChain, NLP, FastAPI and Streamlit to build solutions.