Kumar Shubham — AI Researcher

I build production-grade Agentic AI systems that combine modern backend engineering with large language models to solve real-world problems. I’m an AI Engineer specializing in designing and orchestrating multi-step LLM workflows, retrieval-augmented generation (RAG) pipelines, and scalable backend architectures using Python, FastAPI, PostgreSQL, React, and TypeScript. My work focuses on: • Designing and deploying Agentic AI systems using LangGraph and LangChain • Building RAG pipelines with vector databases and embedding architectures • Orchestrating multi-tool reasoning workflows in production environments • Developing high-performance REST APIs and scalable backend services • Implementing cloud-native deployments with Docker, Kubernetes, and Azure DevOps I operate across the full development lifecycle — from architecture design and experimentation to CI/CD automation, deployment, and performance optimization. With a strong foundation in system design and backend engineering, I focus on building reliable, maintainable AI-native systems that move beyond prototypes and deliver measurable business value. Previously, I contributed to engineering teams at Wipro and LTIMindtree, where I built strong software fundamentals and delivery discipline. I’m particularly interested in AI platform engineering, applied LLM systems, and building scalable AI-driven products that integrate seamlessly into enterprise ecosystems.

Stackforce AI infers this person is a Backend-heavy Fullstack Engineer specializing in AI and cloud-native solutions.

Location: Bengaluru, Karnataka, India

Experience: 2 yrs 6 mos