1
1
India
4+ years of experience
I'm an AI engineer. Most of my work is on multi-agent systems, retrieval pipelines, and LLM apps, plus the full-stack engineering to make them usable — FastAPI and Python on the backend, Next.js/React on the frontend, Postgres and vector databases underneath. I also do a fair bit of 3D and interactive frontend work with Three.js when a project calls for it. I'm quick at prototyping and happy to take on the backend and the model plumbing, or the whole thing if the team needs it.

Contact centers are handing phone calls to AI voice agents, and every one of those calls is recorded. The recordings are valuable for quality reviews, analytics and training, but they are full of names, phone numbers, emails, addresses and card numbers. So they get locked away, or copied into AI tools with the sensitive details still inside. SafeCall solves both halves. Customers talk to Sam, a live billing agent built on AssemblyAI's Voice Agent API: real-time speech in and out, natural turn-taking with interruptions, and tool calls to look up an account, check charges, issue a refund, update contact details or hand the call to a person. When the caller hangs up, SafeCall fetches the session recording and runs it through AssemblyAI Universal-3.5 Pro with speaker separation and PII redaction: personal details become labels in the transcript and silence in the audio, and a second pass looks for numbers and emails the first one missed. Uploaded recordings go through the same pipeline. Only safe artifacts are stored: redacted audio in a private bucket, a speaker-labelled redacted transcript, a PII report and a full audit trail. The original voice session and transcript are deleted from AssemblyAI. AI insights (summary, sentiment, topics, action items and a QA note) come from AssemblyAI's LLM Gateway and only ever see redacted text. Every role sees only what it needs. Customers see their own calls. Support agents work the queue of calls the AI handed over, and each handover carries only its reason, never what was said. Admins search, analyze and export a safe dataset for analytics or AI training, set PII policies and review the audit trail. Built with React, Node.js and Supabase, deployed on Vercel and Railway, and covered by 149 automated tests.
30 Sep 2026