Vinay Jogani

About

I build machine learning systems that survive contact with production. At RSK IT International I work on real-time voice agents running at drive-thrus, toll booths, and parking lots: streaming audio pipelines that chunk live audio at 80-120 ms, detect directed speech, run ASR and intent routing, and answer in under half a second, deployed on-prem and in hybrid edge/cloud setups for 3 production customers and 2 pilots.

Alongside that, I design and ship open-source AI infrastructure focused on making LLM and agentic systems reliable enough to trust: tracewall, a security firewall and flight recorder for AI coding agents; spareloop, a usage scheduler for AI coding CLIs; and production-grade agentic systems built around evals, guardrails, and observability.

Before this I did AI research at Northeastern's Amal Lab (medical image segmentation, 18TB+ multi-omics processing, multi-GPU training) and clinical data science at Brigham and Women's Hospital. I have four peer-reviewed publications on explainable AI, adversarial robustness, and deep learning.

Explore: professional journey · selected projects · technical papers · technical toolkit · academic background · certificates

Contact

Email joganivinay@gmail.com or use the form below; it goes straight to my inbox.