Hi, I'm Vybavnag.
I'm a software engineer at UKG building AI/MLOps infrastructure. That means OpenTelemetry tracing across AI microservices, Go pipelines on GCP, and Pub/Sub feedback loops that turn customer signal into product.
On the side, I'm building Gateway: an AI-native platform where engineers design distributed systems on a visual canvas and ship them to real cloud infrastructure with one click. I wear every hat on it (architecture, microservices, AI agents, Terraform, EKS), and it's taught me more than anything else has.
My background is deep learning (TensorFlow, transfer learning, time-series) and systems (DSP on microcontrollers, SMS→LLM gateways). I like problems that sit at the intersection of ML, infra, and user experience.
I care about the plumbing that makes AI products trustworthy. Telemetry, evals, guardrails, the boring-but-load-bearing stuff.
If any of this sounds relevant to what you're building (AI infra, MLOps, dev tooling, or anything at the intersection of LLMs and real systems), I'd love to grab a coffee →