Available for new missions
I build machine learning systems that leave the notebook and survive the real world.
23
Models in prod
8k
Edge devices
5
Papers
SEC_01Personnel dossier
Machine learning engineer specialising in computer vision and production MLOps. I've deployed models on drones, factory lines and mobile phones, and built the pipelines that retrain them safely. I care about evaluation that reflects reality and systems that explain their mistakes.
SEC_02Mission log
Mission 02 · active
Jan 2023 — Present
@ Orbital Vision
Mission 01
Aug 2019 — Dec 2022
@ Forge Robotics
SEC_03Project holograms
Project_01
Detects crop disease from drone imagery days before it's visible from the ground.
Project_02
Open-source tools for building evaluation sets from real-world model failures.
SEC_04Capability matrix
12 capabilities across 3 systems.
SEC_05Data files
Computer vision workshop
Fusing RGB and multispectral imagery to detect plant disease earlier and more reliably.
Applied ML conference
Quantisation and scheduling strategies that cut energy use without hurting accuracy.
SEC_06Operating protocols
Know what a wrong prediction really costs before choosing a metric.
Evaluation sets built from the real world, not just the easy cases.
Shadow deployments, monitoring and a fast rollback path.
Automated pipelines with checks so models improve without surprises.
SEC_07Training archive
Indian Institute of Science
SEC_08Visual archive
01 / 04keynote // main stage
SEC_09Transmission archive
Example video from YouTube. Add your own talks, product demos or reels here.
Every theme shows videos with a lightweight click-to-play player.
SEC_10Transmission