I am an AI engineer specializing in Computer Vision, Large Language Models (LLMs), and Voice AI. With expertise in object detection, segmentation, and video processing, I have hands-on experience using META AI's Segment Anything Model (SAM) to enhance moving object detection. In NLP & LLMs, I work with models like GPT-4o, Mistral, Llama, Claude, and Gemini, integrating RAG, LangChain, LlamaIndex, and vector databases (Pinecone, Weaviate, Qdrant, OpenSearch) for advanced AI applications. I also deploy solutions on AWS, Azure, and GCP. In Voice AI, I have developed: Real-time voice cloning & voice changer (RVC + React Native + FastAPI) Medical interview analysis AI (Whisper + Claude 2) Voice authentication & speaker recognition API (SpeechBrain + FastAPI) AI voice agent for customer support (Deepgram STT + GPT-3.5 + ElevenLabs TTS + Twilio) Research on speaker diarization improvements (Pyannote) Skilled in Python, Java, and C, I thrive in solving complex problems, optimizing AI workflows, and building real-world applications that push technological boundaries.