I’ve been building production-grade AI systems focused on LLMs and real-time voice agents.
Recent work includes:
End-to-end LLM systems (RAG, tool calling, eval pipelines)
Real-time voice agents (STT → LLM → TTS with streaming + interruption handling)
Scalable backend systems (FastAPI / Node, async workers, Redis queues)
Latency and cost optimization for production AI
Tech stack:
Next.js · FastAPI · OpenAI / local models · Vector DBs · WebRTC · Deepgram · ElevenLabs
What I’m looking for:
AI product teams
Startups building voice or LLM-native apps
Contract or full-time roles
If you’re building something serious in this space,
DM me or comment and I’ll reach out.