Abhinav Sai Kanduri
Generative AI & LLM Engineer | RAG, LLMOps, AI Systems @ Scale | Research-Driven
This profile was put together from Abhinav's public GitHub portfolio, and they haven't joined Vibetown yet, so reach them through their portfolio. Is this you? Contact us to update or remove it.
About
Abhinav Sai Kanduri works in AI engineering, ML & data science and vibe coding & full-stack, based in United States (American Express). Generative AI & LLM Engineer | RAG, LLMOps, AI Systems @ Scale | Research-Driven. Public projects on GitHub include Ai Systems Foundations (AI Systems Foundations documents core concepts, design principles, and real-world failure modes for building…), Customer-Support-AI-Chatbot (Build an AI chatbot for a SaaS or e-commerce company that can understand customer messages, classify intent,…) and Customer-chat-front-end-Ui (An end-to-end AI system design for a customer support chatbot built for SaaS or e-commerce support teams), mostly written in Jupyter, Python and HTML.
Projects 5
Ai Systems Foundations
AI Systems Foundations documents core concepts, design principles, and real-world failure modes for building production-grade AI systems, with a focus on LLMs, RAG, evaluation, LLMOps, and enterprise AI architecture.
github.comCustomer-Support-AI-Chatbot
Build an AI chatbot for a SaaS or e-commerce company that can understand customer messages, classify intent, retrieve company-specific knowledge, answer with citations, call business tools, create tickets, and escalate risky or unresolved cases to humans.
github.comCustomer-chat-front-end-Ui
An end-to-end AI system design for a customer support chatbot built for SaaS or e-commerce support teams. The chatbot understands customer messages, classifies intent, retrieves company-specific knowledge, answers with citations, calls business tools, creates support tickets, and escalates risky or unresolved cases to humans
github.comGenerative_ai_course
ML | DL | NLP | LLM | RAG | AGENTS | MCP
github.comPortfolio
AI Engineering portfolio focused on GPU infrastructure, LLM inference, model benchmarking, distributed systems, agentic AI, and robotics. Featuring hands-on implementations, research analysis, architecture designs, performance experiments, and production-oriented engineering projects.
github.com