Shoury Sharma — Software Engineer

I’m a Software Engineer focused on building production-grade Generative AI systems and LLM infrastructure at scale. Currently, I work as Member of Technical Staff 2 at Nutanix, where I help design and deploy AI-driven infrastructure features for Nutanix AI (GPT-in-a-Box)—with a strong emphasis on scalable LLM serving, secure access (OAuth2 + OIDC), and high-performance containerized microservices. My work has directly improved inference latency and system reliability in enterprise AI environments. Before this, I spent over two years at Katonic.ai, where I built and shipped multiple enterprise GenAI applications, including RAG systems, multi-agent workflows, and analytics platforms for tracking model usage and cost. I’ve worked extensively with LangChain, vector databases (Pinecone, FAISS), Kubernetes, and cloud-native deployments on GCP, collaborating closely with ML teams to take ideas from prototype to production. I enjoy working at the intersection of LLMs, backend systems, and cloud infrastructure—turning complex AI workflows into reliable, scalable products. I’m particularly interested in LLMOps, RAG architectures, AI agents, and platform engineering for GenAI. If you’re building or scaling AI systems and want to exchange ideas, feel free to connect.

Stackforce AI infers this person is a SaaS-focused Software Engineer specializing in Generative AI and infrastructure development.

Location: Bengaluru, Karnataka, India

Experience: 3 yrs 4 mos