Data platforms. AI systems. The infrastructure between them.
delta at Google Cloud, leading Data & AI innovation and transformation across Southeast Asia. I publish research on multi-agent systems, inference optimization, and AI safety, and write the practitioner's notes behind it, from inside real production systems.
01 Now
ICLR 2026 paper on LLM safety, and compute primitives for orbital environments.
New ventures at the frontier; conversations with research labs and founders.
Fused MoE kernels, circuit tracing in production, and bets on model honesty.
02 Latest
What Runtime Interpretability Actually Costs, Part 1: The Case for Measuring It
Everyone assumes activation probes are too expensive to run in production. I ran the numbers on paper and I no longer believe it. Here is the argument, my predictions, and the harness I built to settle it.
Read the essay →03 Selected writing
04 Research focus
Multi-agent systems
Coordination, debate, and verification for AI that runs unattended.
/ 02Inference optimization
Fused MoE dispatch, speculative decoding, custom Triton kernels.
/ 03AI safety & interpretability
Circuit tracing, activation steering, sandbagging detection.
/ 04Distributed systems
Formal synthesis and correct-by-construction architectures.
05 Selected publications