Professional Overview
I’m a Machine Learning Engineer specializing in NLP, LLM systems, and Generative AI, with a strong focus on building scalable, production-grade AI solutions that drive real-world impact. My work centers on designing intelligent systems that automate complex workflows, enhance decision-making, and deliver measurable business value.I began my career in engineering-focused environments, where I developed a strong foundation in structured problem-solving, large-scale system thinking, and working within complex technical ecosystems. This background now informs my approach to building robust, reliable, and efficient AI systems.Transitioning into Machine Learning and AI, I have built end-to-end ML pipelines, agentic LLM workflows, and scalable automation platforms. At Neuranize, I have engineered: • An agentic influencer discovery system using LangGraph, reducing research time by 65% • An automated outreach generation engine, cutting manual effort by 70% • An LLM-powered influencer matching system, improving campaign setup efficiency by 50%My technical stack includes Python, PyTorch, TensorFlow, Hugging Face, LangChain, LangGraph, vector databases, and RAG architectures, supported by strong MLOps practices using FastAPI, Docker, MLflow, GitHub Actions, and AWS.I’m deeply interested in building production-ready AI systems, especially in areas involving LLM agents, intelligent automation, and scalable AI infrastructure. I enjoy working on problems that sit at the intersection of machine learning, systems design, and real-world deployment.If you’re building advanced AI systems or exploring next-generation intelligent applications, I’d be glad to connect and collaborate.Currently focused on designing agentic LLM systems, scalable RAG architectures, and AI platforms ready for real-world deployment.