Type to search posts and projects to navigate

Subhadip Mitra · Google Cloud

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

Building

ICLR 2026 paper on LLM safety, and compute primitives for orbital environments.

Exploring

New ventures at the frontier; conversations with research labs and founders.

Writing

Fused MoE kernels, circuit tracing in production, and bets on model honesty.

What I'm up to →

02 Latest

§ INTERPRETABILITY · ESSAY · Jul 2026

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

All essays in the archive →

04 Research focus

05 Selected publications

2026
Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs
arXiv
PDF →
2026
Cross-Platform Fused MoE Dispatch in Triton: Portable Expert Routing Without CUDA
arXiv
PDF →
2026
Spark-LLM-Eval: A Distributed Framework for Statistically Rigorous Large Language Model Evaluation
arXiv
PDF →
2026
Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety
ICLR 2026 Workshop AIWILD
PDF →
2026
Field-Theoretic Memory for AI Agents: Continuous Dynamics for Context Preservation
arXiv
PDF →
All publications →
Subhadip Mitra