A 20-year-old engineer-in-training building across Electrical Engineering, Machine Learning Systems, and the odd competitive-programming contest in between — currently researching privacy-preserving federated learning over unreliable networks.
I'm Barad Dhanush — a tech enthusiast who ended up studying Electrical Engineering and never quite stopped exploring everything adjacent to it. My core interests sit across Competitive Programming, Math, Finance, Machine Learning and AI, and the electronics/electrical core that got me here in the first place — and lately I've been poking around Consulting, Product Management, and Quant to see where else that curiosity leads.
Right now that curiosity has a fairly specific shape: making distributed Machine Learning Systems work reliably and privately even when the network underneath them isn't cooperating.
July 2025 — July 2030 (expected) · Currently a sophomore
A summer spent making privacy-preserving mean estimation robust to unreliable, intermittently-connected relays — the kind of failure real deployments actually have.
Working at the intersection of relaying, differential privacy, and federated learning within Machine Learning Systems — extending semi-decentralized, privacy-preserving mean estimation to stay robust when links drop or relays misbehave. The paper is being finalized for submission; the full write-up will go up here once it's out.
Actively looking right now — happy to talk to labs or industry research teams.
Planning ahead for another dedicated research stint next year.
A few projects are underway alongside research and coursework. Write-ups, code, and demos will be added here as they wrap up.
Details, tech stack, and links coming soon.
Details, tech stack, and links coming soon.
Details, tech stack, and links coming soon.
Check back soon, or reach out directly for a walkthrough of what's cooking.
Where most of my thinking time goes.
What I do when I close the laptop.



Open to remote or corporate research internships now, and on-site research opportunities in May–July 2027. Reach out any time.