All work
Full-platform engineer + product / project lead (team of 2–3)
Kumush AI — AI Front Desk Platform (Chat · Voice · Workflow)
2025–2026 · In production
An AI front desk platform where one agent handles customers across chat, phone, and automation — completing orders, forms, and API actions mid-conversation. I worked across the whole platform: the production voice AI stack, the embeddable chat widget, and the automation layer, and I led the product and project for a team of two to three.
Highlights
- Real-time multilingual voice (Uzbek / Russian / English) on LiveKit; perceived response latency cut via MCP tool caching + TTS chunking.
- Voice stack built from modular STT → LLM → TTS layers, not a single speech-to-speech API — multi-provider with automatic model fallback.
- Inbound / outbound telephony (LiveKit, SIP/PSTN) plus SMS.
- Reception layer: forms and workflow automation — AI screening, calls, email, human review, Google Sheets writeback.
- RAG knowledge base and shared MCP tools across both chat and voice.
- Continuous reliability layer: automatic model fallback, latency observability logged to Postgres, migration versioning (dbmate).
- Benchmarked real-time STT providers and tuned custom NER for local place names.
In production
- 7,000+ customers served via Kumush Chat on Wakil AI — Central Asia’s first sovereign legal AI platform, citation-backed to official Uzbek legal sources (~3,000 daily active users).
- 90%+ conversation completion rate on a live client screening flow.
- Powers the admissions pipeline and outbound pre-interview voice campaigns for Humblebee AI Academy.
- 3 languages live in production.
