Aakash Agrawal

Building the platforms & infrastructure AI runs on

I work in the unglamorous middle layer of AI, turning research and prototypes into systems teams can depend on. 0→1 is my default: ML platforms, agentic and GenAI infrastructure, and the whole path to production.

More about me →

Latest

Nov 4, 2026

Trust, then verify: a guardrailed LLM agent for edge AI fleets

The agent is the easy part: a deny-by-default policy gate, verification, rollback, and an eval the model can't game.

Oct 31, 2026

Gurukul: Serving and Observing a Robot Policy

A policy server, Prometheus and Grafana, and a slow server on purpose — 9 of 20 served.

Oct 20, 2026

Gurukul: Teaching a Robot Arm by Imitation, from Scratch

45 demonstrations, an ACT policy, and 10 of 20 on the real arm — most failures trace back to data.

All writing →

Selected Projects

Grafana dashboard during the served evaluation: control rate at 30 Hz, zero deadline misses, action queue refilling, chunk round trip about 70 to 87 ms

Gurukul: A robot learning stack on a real arm

One low-cost SO-ARM101 arm, built up one project at a time with Hugging Face LeRobot: imitation learning, serving and observability, and data curation at scale.

Edge Agent Ops

Edge Agent Ops

A guardrailed LLM agent that monitors a fleet of edge AI inference nodes, diagnoses faults, and remediates them only within hard policy limits. Ships an evaluation harness and a live Prometheus + Grafana observability stack.

All projects →