As a Senior Platform Engineer with 3 years of experience, I specialize in creating scalable, secure, and high-performing cloud platforms to drive efficiency and performance at scale. Skilled in Kubernetes, CI/CD automation, and cloud architecture, I focus on transforming monolithic applications into robust microservices, achieving 99.9% uptime and significantly reducing downtime and processing time through GPU-optimized solutions.At Quantiphi, I’ve led the deployment of large-scale models, supporting over 200,000 daily requests and delivering solutions that reduce setup times and streamline infrastructure. My recent projects include an advanced Model Inferencing Platform using NVIDIA Triton and NeMo microservices, handling half a million requests daily, and a centralized Speech Service Platform integrating ASR, TTS, and NMT models for seamless real-time speech applications.With expertise across Azure, GCP, and NVIDIA platforms, I’m passionate about utilizing emerging technologies to build platforms that enhance reliability, scalability, and compliance, always striving to stay ahead in the rapidly evolving MLOps landscape.