ABOUT

I'm an AI Engineering leader focused on building production-grade intelligence.

Over the past 16+ years, I've designed and deployed AI systems across banking, healthcare, and the public sector — building the MLOps, LLMOps, and governance infrastructure that takes models from research into real-world environments.

Today, my work centers on AgentOps and multi-agent systems: making agents reliable, measurable, and aligned with business KPIs at scale. I design evaluation frameworks, guardrails, and red-teaming strategies to ensure LLM-powered systems operate safely in regulated environments.

I also work at the systems layer — optimizing LLM inference and hardware performance across GPUs and TPUs, writing Triton and JAX/Pallas kernels to push efficiency and throughput.

I lead AI Engineering across APAC at IBM. Beyond enterprise deployments, I help shape global standards for multi-agent AI evaluation as Vice Chair of IEEE SA IC25-003™ and serve on the GSDC Technical Advisory Board. I maintain RLM-Codelens and contribute to open-source systems work.