Kollaikal Rupesh — Founder

I build real-time voice AI systems where model behavior, latency, and robustness matter as much as raw capability. As a Founding AI Engineer, I specialize in low-latency streaming inference architectures for conversational systems, optimizing throughput, analyzing latency–accuracy tradeoffs, and designing reliability primitives that prevent silent failure in production inference pipelines. My work spans: • Optimizing streaming speech pipelines (ASR → LLM → TTS) for sub-second response time under production-level load • Instrumenting fine-grained latency profiling (P50/P95) and diagnosing stage-level bottlenecks • Building evaluation frameworks measuring WER stability, partial transcript drift, and real-world inference behavior • Designing failover and liveness mechanisms that improve uptime consistency in distributed AI systems • Fixing silent degradations due to real-world constraints like sample-rate mismatches and back-end variability I’ve contributed to the open-source voice AI framework Pipecat, including: • Fixing Smart Turn v3 prediction failures at non-16 kHz sample rates via high-fidelity resampling (soxr VHQ), improving endpoint detection accuracy from 59% to 94% on telephony test sets • Correcting pipeline processor duplication logic to ensure frame-chain integrity • Designing heartbeat timeout detection and failover strategy abstractions to improve liveness and resilience • Reducing high-frequency audio logging overhead under streaming workloads • All changes merged into main with full test coverage I’m interested in speech modeling, inference robustness, and scalable real-time reasoning systems that work reliably in messy real-world environments.

Stackforce AI infers this person is a Backend-heavy AI Engineer specializing in real-time voice systems and scalable architectures.

Location: San Francisco, California, United States

Experience: 3 yrs 6 mos