꧁ Hello everyone! ꧂ I'm a Senior Voice AI Engineer focused on building real-time conversational systems and scalable audio infrastructure. I specialize in low-latency voice pipelines, streaming LLM integrations, and production-grade backend systems that power live conversational experiences. My work centers on reliability, latency optimization, and stateful voice workflows designed for real-world deployment.

What I Build
    • Real-time Voice AI systems with streaming ASR + LLM orchestration
    • Low-latency audio pipelines (<800ms response budgets)
    • Conversational state management and interruption handling
    • Voice-enabled automation and structured backend execution
    • Scalable event-driven architectures for live session environments
Technology Focus
    • Python, TypeScript, FastAPI, React, Next.js
    • WebSockets, streaming architectures, async processing
    • LangChain / LLM orchestration
    • PostgreSQL, Redis, distributed task queues
    • AWS & GCP cloud deployments
    • Observability, fault tolerance, and reliability engineering

I focus on building voice systems that feel fast, natural, and dependable - not just technically impressive, but production-ready and scalable. If you're building voice agents, AI call automation platforms, or conversational infrastructure, I'd love to connect and explore opportunities.