Voice AI
Gateways
Real-time conversations over the phone — ASR, TTS, barge-in, intent on top of SIP/WebRTC telephony.
I'm Santosh Varma — AI Architect at Kore.ai. I design the voice gateways, RAG pipelines, and agent runtimes underneath the AI products Fortune 500s actually deploy.
↑ That gap is where I work.
Real-time conversations over the phone — ASR, TTS, barge-in, intent on top of SIP/WebRTC telephony.
Retrieval that actually retrieves. Semantic + lexical, re-rankers, grounded-response eval at every step.
Autonomous agents that get real work done — tool-use, policy auth, recoverable state, runtime observability.
The unsexy infra that lets the interesting work survive: routing, isolation, cost/latency budgets, eval pipelines.
"I architect the production AI underneath the chatbot you'll eventually call when your bank app freezes — and I make sure the answer it gives you is the right one."
— SV, on the job description
Trusted by teams shipping AI at
Reference architectures for voice AI, RAG, and agentic workflows across the XO Platform — AgentAssist, SmartAssist, SearchAssist, Voice AI.
Modernised a legacy monolith into event-driven microservices. Redesigned the Sitelink (FMS) integration end-to-end.
Multi-party white-label commerce platform & a video-based patient-doctor telehealth product. Honolulu.
Autonomous micro-agents for workflow automation. Hybrid retrieval, task orchestration, context-driven execution.
A small agent grounded on my résumé, capabilities, and case studies — running entirely in your browser. Recruiters: interrogate it. Founders: ask it how I'd approach your problem.
Hi — ask me anything about my work or how I'd tackle a problem you're stuck on. I'll keep it concrete and short.
If the model can't answer it well, the system says so. Eval is a first-class part of the architecture, not a metric you add later.
A 200ms answer that's "good enough" beats a perfect answer at three seconds — especially over voice. I design to the budget first.
Routing, isolation, observability, recovery. The interesting work only stays interesting because the boring parts are bulletproof.
Every model, every provider, every chunking strategy gets swapped within 12 months. I architect for the swap, not the commitment.
A platform that depends on one person knowing how it works is a platform with a single point of failure. I leave teams stronger.
Architecting AI-enabled voice gateways on the Kore.ai platform — ASR, TTS, SIP/WebRTC telephony, real-time streaming, and LLM-driven intent resolution powering enterprise voice agents.
Implemented process improvements resulting in a 20% reduction in issue resolution time.
Led evaluation and enhancement of software/hardware interfaces, resulting in a 30% improvement in system performance and reliability.