AI Systems
Building intelligent systems at the intersection of research and production
delta at Google Cloud — Data & AI innovation and transformation across 6 countries in Southeast Asia. Publishing research on multi-agent systems, inference optimization, and AI safety. Exploring what's next.
Now
What I'm up to →Building
Multi-agent frameworks for enterprise AI. Inference optimization. Production safety tools.
Exploring
New ventures at the frontier. Conversations with research labs and founders building what's next.
Writing
Notes on circuit tracing, distributed systems synthesis, and lessons from shipping AI at scale.
Research Focus
01
Multi-Agent Systems
Coordination protocols, debate frameworks, verification for enterprise AI
Read about Agent Protocol Stack →02
Inference Optimization
Speculative decoding, Triton kernels, computational efficiency at scale
Read about Triton Kernels →03
AI Safety
Mechanistic interpretability, circuit tracing, sandbagging detection
Read about Circuit Tracing →04
Distributed Systems
Formal synthesis, correct-by-construction architectures
Read about UPIR →Selected Publications
View all →- 2026
Automated Rule Generation for Tiered Systems Using Multi-Stage Failure Learning
Google, Technical Disclosure Commons - 2026
Predictive Cost-Benefit Routing for Multi-Tier Risk Decisioning Systems
Google, Technical Disclosure Commons - 2025
UPIR: Automated Synthesis and Verification of Distributed Systems
Google, Technical Disclosure Commons - 2025
ETLC: A Context-First Approach to Data Processing in the Generative AI Era
Google Cloud
Recent Writing
View all →- OpenAI's Confessions Paper Has a Blind Spot. Here's What Fills It.February 2026
- Activation Steering in 2026: A Practitioner's Field GuideFebruary 2026
- Moltbook as MCP Stress Test: What 770K Agents Reveal About Protocol DesignFebruary 2026
- Circuit Tracing for the Rest of Us: From Probes to Attribution Graphs and What It Means for Production SafetyJanuary 2026
- RLVR Beyond Math and Code: The Verifier Problem Nobody Has SolvedJanuary 2026
- The Agent Protocol Stack: Why MCP + A2A + A2UI Is the TCP/IP Moment for Agentic AIJanuary 2026
Building something interesting? Let's talk.