Build AI that shipsMeetJariwala
Selectedwork,shippedandrunning
Predicting end-of-turn before the silence.
Omni Turn Detector
RustONNXWebRTC
Omni Turn Detector. Rust, ONNX, WebRTC.
Built for production.
Every number here maps to something running in production, not a slide.
CURRENT FOCUS
AI INFRASTRUCTURE
Building inference systems at scale.
It all ships. Zero demos.
10-20ms
Worked for low latency infrastructure
21,584+
Hours of audio processed
- Builder
- Creator
- Speaker
MJ
Meet Jariwala
“I'd rather ship one real system than demo ten. My edge is simple: I notice what others miss, and I build like it's already live.”
Meet Jariwala
Everything I actually work in.
Speech Domain, Models at scale: WHISPER VOICE AI DIARIZATION VAD END-OF-TURN STT TTS VOICE-CLONING Inference, Serving at scale: CONCURRENCY INFERENCE SERVER LLM THROUGHPUT LATENCY STREAMING REAL-TIME Making it fast, Optimization at scale: CUDA GPU QUANTIZATION ONNX TENSORRT METAL GGUF SAFETENSORS Languages, What I build in: PYTHON RUST Over the wire, Transport and queues: gRPC WEBSOCKETS HTTP STREAMING Retrieval, Context engineering: RAG EMBEDDINGS VECTOR DB RANKING MEMORY COMPRESSION Running in prod, Infrastructure: DOCKER POSTGRES REDIS MONITORING EVALS PIPELINES Shipped work, Products, not demos: VOICE AGENTS INFERENCE SERVER TURN DETECTOR MODELS DOCUMENTPORTAL MILLION HOURS DATASETS Craft, How it feels to use: UI WEB WORKFLOW STORYTELLING SYSTEMS Off the keyboard, The other half: SPEAKER WRITER MENTOR CREATOR BUILDER About, Meet Jariwala: AI THAT SHIPS SYSTEMS PROOF SCALE SHIPPING
Selected work
Omni Turn Detector
Predicting end-of-turn before the silence.
