Rikhil Nellimarla
> building voice agents, agentic backends, and things that ship
AI and backend engineer with a background in electronics. I build real-time voice AI systems, multi-agent architectures, and the telephony infrastructure that connects them to the real world. Currently a 3rd-year ECE undergrad at VIT Amaravati.
> experience
TargetDial
Jan 2026 – Feb 2026Built and shipped production AI voice agents integrated with SIP/Asterisk/FreePBX telephony stacks for inbound lead qualification and outbound follow-ups. Designed end-to-end call workflows spanning voice → intent detection → CRM actions → calendar booking with GoHighLevel and n8n automations.
Indominus Labs
May 2025 – PresentPioneered SIP trunking integration to bridge LiveKit with legacy telephony providers (VICIDIAL). Engineered a scalable data pipeline on bare-metal GH200 to process 1M+ customer call logs with Whisper v3 transcription, PII sanitization, and multi-agent performance analysis.
Stealth VC Project
Jun 2025 – Sep 2025Developed a custom turn-detection model for Hindi, overcoming a core LiveKit SDK limitation for non-English voice agents. Architected scalable telephony infrastructure using Asterisk as middleware to route calls to various endpoints including WhatsApp.
Clink
May 2025 – PresentBuilt a full-stack AI backend orchestrating 8+ specialized agents for analysis, chat, forecasting, and image generation — serving 80+ onboarded cafes. Production infrastructure with PostgreSQL, Redis, S3, and full async observability via Logfire.
Open Source Community (Mozilla), VIT
May 2025 – PresentLeading 100+ student developers in open-source practices. Conducting workshops on WebRTC, API Design, and Backend Development. Overseeing 6 open-source projects with technical roadmap and code review processes.
> projects
Kinesys-CRM
Full-stack CRM with AI-powered voice agents for inbound/outbound calls, Google Calendar integration, and real-time lead management via WebSockets.
VISU-X
Multimodal AI backend for a humanoid robot — vision transformers, hybrid memory with pgvector, real-time speech via WebRTC, and facial recognition.
VoiceIQ
Enterprise call log processing with self-hosted Whisper v3 transcription, PII sanitization, and multi-agent analysis for generating reports and insights.
Multi-Agentic Graph RAG
Graph-based RAG system using Neo4j for knowledge retrieval with agentic reasoning, deep research via DuckDuckGo, and visualization of reasoning paths.
IntelliPost
AI-powered postal mail sorting using OpenAI Vision for address extraction, India Post's Pincode API for smart routing, and Cloudflare R2 for storage.
Lexalytics
Backend for the Ministry of Corporate Affairs — legislative sentiment analysis with PDF upload, AI summarization, and batch CSV processing using GPT-4.1.
// other things i've built
- MemoryWeave — Real-time object detection streams converted to AI-generated stories. <100ms latency. Winner @ HackSRM 2024
- Converso — Voice-based conversational RAG on an ESP32-S3 IoT device. Records, transcribes, and retrieves from past conversations.
- Dungeons & Fallacies — Text-based RPG where combat is a logical debate. AI judge evaluates argument soundness against a "Null Hypothesis."
- Pixy — Self-hosted AI Discord bot for 100+ members with persistent per-user memory via pgvector. NGINX · Supabase
- Terminal Chatbot — CLI chatbot with bash execution tools and a rich Textual TUI. Groq · Textual
> skills
> achievements
- Presented the VISU humanoid robot to the Chief Minister of Andhra Pradesh, Mr. Chandrababu Naidu, at VLaunchPad.
- Winner, HackSRM 2024 (Open Innovation track) for the MemoryWeave project.
- 3rd Place, Post-a-thon at VIT-AP — showcased IntelliPost to Union Minister Shri Chandra Sekhar Pemmasani.
- Technical talks to 100+ attendees on agent architectures and LLM security at Null Vijayawada, NIT Warangal, and SRM University.
- Led the tech team for AP CID home guard exams — backend and on-site infrastructure.