I’m an AI Engineer specializing in LLMs, NLP, and applied machine learning, building production-ready systems that power intelligent assistants, automation pipelines, and data-driven decision-making. I work across **multimodal AI (text, voice, and video)**—developing solutions like conversational agents (OpenAI/GPT, LangChain), speech systems (Whisper, ElevenLabs), and video/vision pipelines (OpenCV, diffusion models), with strong backend integration using Python, FastAPI, and cloud platforms like AWS and GCP. My focus is on end-to-end applied AI, from model fine-tuning and prompt engineering to scalable deployment (Docker, Kubernetes) and real-world use cases such as AI-powered CRMs, voice bots, and intelligent document processing.