Generative AI Engineer with around 9 years of experience designing, developing, and deploying AI-driven solutions using large language models (LLMs), multimodal AI, and deep learning architectures. Proven track record of building end-to-end AI pipelines, optimizing model performance, and integrating Gen AI solutions into enterprise systems. Skilled in retrieval-augmented generation (RAG), prompt engineering, and vector database integration to build intelligent, context-aware AI solutions. Hands-on expertise with OpenAI, Hugging Face Transformers, LangChain, and cloud AI services (AWS SageMaker, Azure AI, Vertex AI). Adept at designing end-to-end AI pipelines, from data preparation and model training to production deployment and performance monitoring. Track record of reducing operational costs and accelerating delivery timelines through AI-driven automation and creative content generation. Strong collaboration skills, working with cross-functional teams to integrate AI capabilities into products and workflows seamlessly. Designed and deployed multi-agent AI systems for complex problem-solving using frameworks like LangChain Agents and Auto-GPT. Experienced in building domain-specific knowledge bases and integrating them with LLMs for context-rich responses. Developed multi-turn conversational AI with memory and personalization for customer engagement platforms. Implemented few-shot and zero-shot learning techniques to improve model adaptability without extensive retraining. Integrated vector search technologies (Pinecone, Weaviate, Chroma) with LLM pipelines for lightning-fast context retrieval. Created custom embeddings and semantic similarity algorithms to enhance AI reasoning and search capabilities. Experienced in cost optimization for LLM-based services, reducing inference costs through quantization and model distillation. Collaborated with data science and product teams to translate AI research into user-facing, revenue-generating solutions. Passionate about advancing Gen AI technologies to enhance personalization, automation, and decision-making at scale. Experienced in fine-tuning and optimizing LLMs (GPT, LLaMA, Mistral) for domain-specific applications, improving accuracy and relevance. Built custom AI-powered chatbots and virtual assistants leveraging RAG, embeddings, and semantic search for enhanced user interaction. Skilled in model evaluation, A/B testing, and implementing feedback loops for continuous AI performance improvement. Implemented scalable AI architectures using Docker, Kubernetes, and CI/CD pipelines for reliable production deployments. Leveraged Whisper and speech models for building real-time transcription, summarization, and voice-based applications.