Agentic AI
Designing and leading production-grade agent workflows, assistants, and evaluation strategies.
SS
Creator of LLMasJudge
Sarath Surya
AI, data, and software engineering leader focused on turning emerging technology into useful, responsible products.
Sarath has around 20 years of experience across software engineering, data platforms, analytics, and artificial intelligence. His current work centers on agentic AI, engineering leadership, production architecture, evaluation, security, governance, and the practical adoption of AI-assisted development.
20+Years in technology
8Patents
RaleighNorth Carolina
Why this project
Evaluation should be easier to reuse.
LLMasJudge started from a simple need: give developers a clear, provider-independent way to evaluate AI responses, RAG systems, and agents without rebuilding the same foundations for every project.
Experience
Where the work connects.
Data engineering
Building the platforms and integrations that ground AI systems in reliable enterprise data.
Responsible delivery
Applying security, governance, human review, cost controls, and measurable quality standards.
Engineering culture
Helping teams adopt AI development tools while keeping strong review and delivery practices.
Education
Technical and business foundation.
Executive MBA
Purdue University
Master of Science, Computer Science
The University of Texas at Arlington