I am a GenAI-focused AI/ML professional working on production-grade AI systems, with a strong focus on agentic AI, LLM-based applications, and Retrieval-Augmented Generation (RAG). My work spans the full lifecycle of AI system development—from architecture and orchestration to optimization, secure deployment, and real-world adoption.
I actively design and build agentic AI systems using frameworks such as LangGraph and LangChain, implementing multi-agent workflows for planning, tool use, reasoning, and execution. These systems are applied to complex enterprise use cases where autonomy, reliability, and control are critical.
I also work extensively on open-source LLM hosting and inference, including on‑prem and air‑gapped deployments, enabling organizations to run GenAI securely without external data exposure. This includes model selection, quantization, inference optimization, vector search integration, and cost–latency trade-off analysis.
I hold a Ph.D. in Engineering, which gives me a strong foundation in applied machine learning, data-driven modeling, and constraint-aware system design. This background influences how I build AI solutions that are robust, interpretable, and reliable under real-world constraints.
I operate as a hands-on individual contributor, deeply involved in solution design, architectural reviews, PoCs, demos, and production delivery, translating complex requirements into scalable and secure AI architectures deployed across cloud, on‑prem, and secure environments.
I enjoy working at the intersection of engineering, agentic intelligence, and real-world delivery, building AI systems that are not only technically strong but also practical, compliant, and business-ready.
If you’re working on GenAI platforms, agentic AI systems, or open-source LLM deployments—or exploring how to adopt these responsibly at scale—feel free to connect or reach out.
