Jun 2025 – Aug 2025 · 2 mos · On-site

• During my internship at DRDO’s Solid State Physics Laboratory, I designed and trained a Large Language Model (LLM) similar to ChatGPT using Python, PyTorch, Hugging Face Transformers, and CUDA-accelerated GPUs. The model was fine-tuned on domain-specific datasets to perform context-aware text generation, summarization, and question-answering. I implemented efficient tokenization pipelines, optimized training with mixed-precision techniques, and integrated attention mechanisms to improve coherence and factual accuracy. This project strengthened my expertise in deep learning, natural language processing, and large-scale model deployment.