Summary
Jayanth Kulkarni is a Senior Software Engineer specializing in MLE/MLOps with 8 years of experience building production-grade ML systems, Kubernetes infrastructure, and NLP research. At Avesha he has shipped automated deployment pipelines, containerized LLM inference on GPU clusters, and an admin dashboard that monitors 50+ customer clusters with real-time alerting. His work on predictive scaling models and smart-scaler Helm charts improved autoscaling accuracy by 15% and cut enterprise onboarding from hours to minutes. A research background (NeurIPS 2019, IISc, and an MSc thesis in applied ML/NLP) underpins practical innovations like a novel terminology-extraction algorithm and reinforcement-learning approaches to load balancing. Comfortable across AWS, KServe, ArgoCD, Helm, Ray and Prometheus, he blends hands-on engineering with reproducible research to move models from prototype to resilient production. Colleagues describe him as the bridge between research-grade algorithms and opinionated, scalable MLOps practices.
9 years of coding experience