About Me
Hi, I'm Kamal Nayan.
I'm currently pursuing my B.Tech in Data Science & AI from IIIT Dharwad.
My primary interest is AI engineering — building AI systems that can be integrated into real-world products.
Recently, I worked as an AI Engineer Intern at HobbyFi, an AI CRM platform. I integrated APIs like Gemini, Meta, WhatsApp, Plivo & LiveKit, and worked on AI agents including an AI receptionist (inbound and outbound — WhatsApp and voice) and an AI copilot with controlled read/write access.
Alongside that, I've been building an SLM project — a 114-million-parameter decoder-only transformer model built from scratch.
Overall, I enjoy working at the intersection of AI and software engineering.
education
iiit dharwad · in
base
IIIT Dharwad — B.Tech, Data Science & AI
admitted
2023 — graduating May 2027
gpa
8.83 / 10.0
focus
AI engineering · LLMs · full-stack
Resume
The one-page version.
Experience
Where I've worked.
HobbyFi
May — Jul 2026 · Remote
AI Engineer Intern
AI CRM
My core work — production AI agents wired into real APIs, and the guardrails that keep them reliable.
- AI Receptionist — Answers business calls, texts on WhatsApp (Meta API), and handles voice calls (Plivo, LiveKit) — booking customers end-to-end.
- HobbyFi Copilot — Dual read/write agent under guardrails — write actions only fire after webhook-driven vendor confirmation.
- AI Morning Brief — A daily agent built on the same integration layer, keeping owners briefed without manual digging.
- Page-Creator — Self-serve module that lets businesses spin up their own landing pages.
Learnings: Production API integration, webhook-driven writes, and shipping under real deadlines.
TypeScript · Next.js · Mastra · Firebase · Plivo · LiveKit · Meta API · Qdrant
Buddhi AI
A side project inside HobbyFi — a company memory platform where agents agree on verified facts before writing anything.
- Memory Platform Backend — RBAC, cross-agent conflict resolution, and a fact registry that governs who can read and write what.
- MCP + CLI — Shipped the memory layer as MCP and CLI tools, with OAuth logins into Google Workspace, Notion, GitHub, and Slack.
Learnings: Access-control design and memory systems that other agents consume.
TypeScript · Neon · Qdrant · FalkorDB · Resend · OAuth
Projects
Things I've built.
Current project
AI Courtroom
Making legal practices easier and accessible with AI agents.
Skills
What I work with.
Languages
AI / ML
Frameworks & Web
Data & Storage
DevOps & Tools
AI Tools
Contact Me
Let's talk.
Open to internship and grad roles in AI engineering and software engineering.