Enterprise Agent Platform
Building enterprise Agent platforms from runtime and tool governance through evaluation and operations, bringing LLMs reliably into core workflows.
Architecture evolution, production operations, and team delivery.
Architecture decisions, platform delivery, quality operations, and lessons.
Owned a cross-industry AI Agent customer-service SaaS platform from architecture evolution through production operations and expanded the team AI development harness across 40 repositories.
Built and delivered a multimodal data-labeling and model-serving platform from 0 to 1, connecting training data, model artifacts, auto-labeling, quality validation, and serverless inference.
Owned web engineering, microservice decomposition, model-serving call chains, and platform operations for 0-to-1 generative AI SaaS delivery.
Replay evaluation, data feedback, and policy optimization.
Built reproducible Agent regression evaluation from production traces for prompt, tool, and model changes.
Read moreFocused on platform architecture, service scale, team governance, and delivery outcomes.
Owned a cross-industry AI Agent customer-service SaaS platform from architecture evolution through production operations, supporting 2k+ tenants, 230k+ users, 60k peak requests/day, and 70%+ customer-issue auto-resolution.
Led model-driven Agent Runtime 2.0 across Agentic RAG, parallel multi-agent orchestration, and unified context; held end-to-end latency around 7s under 7k+ average conversation-token load while reducing token consumption by 60%.
Led a 3-person Agent squad in platform delivery and expanded the AI development harness across 40 repositories, establishing specification, review, acceptance, and release governance.
Contact
Focused on Agent Runtime, tool governance, evaluation release gates, and core workflow integration.