- Architected and implemented Maya, an AI Secretary, end to end: 7 microservices across Go, gRPC, Python, FastAPI, Asynq and LangGraph.
- Designed a novel tool-routing architecture that lets the LLM reach 50+ functions through just 2 tools.
- Architected and implemented the core campaign execution and concurrency-management systems for Agni, Ravan.AI's advanced Voice AI platform.
- Supported 1,000+ concurrent calls using a hybrid scheduler and queue architecture.
- Designed concurrency controls spanning the model, WebRTC, telephony and infrastructure layers.
- Worked extensively with SIP, RTP, telephony and PBX systems in the Voice AI call path.
- Architected and scaled CloserX using Django REST Framework, Python, RabbitMQ and Celery.
- Redesigned the asynchronous calling pipeline, increasing outbound concurrency from 5 to 300 — a 60× increase — using distributed task processing, priority-based queuing and optimised call orchestration.
- Scaled infrastructure to support 50K+ AI calls per day.
- Designed and operated fleet-based LiveKit infrastructure for real-time Voice AI, with geo-routing, manual overrides and self-healing.
- Managed LiveKit server capacity dynamically without relying on Kubernetes.
- Proposed, architected and built two platforms from 0 → 1: a Shopify AI Agent and an internal analytics dashboard.
- Migrated production services from Docker-based deployment to MicroK8s.
- Go
- Python
- gRPC
- FastAPI
- Django REST Framework
- Asynq
- LangGraph
- RabbitMQ
- +11