chiranjeevi@ai: ~

Chiranjeevi Gundu

AI Engineer

AI Engineer and systems architect with an M.S. in Computer Science (AI track) and 4 years of experience taking AI from prototype to production. I design end-to-end GenAI systems — multi-agent orchestration, RAG pipelines, and model-routing layers — and ship them with backend rigor: typed APIs, automated tests, CI/CD, and secure cloud and on-prem deployment on AWS and Azure.

View Experience GitHub LinkedIn

Professional Experience

AI Engineer

Axitem Software Solution Inc. | Aug 2025 – Present

  • Deliver AI chatbots and document Q&A tools (Python, LangChain, OpenAI APIs) that answer client questions from internal documents in seconds, relied on daily by client support and operations teams.
  • Ship RAG pipelines (Pinecone vector search, PostgreSQL) that ground every chatbot answer in real company documents with source citations, cutting hallucinations and earning formal client sign-off.
  • Automate multi-step business tasks with LangChain and LangGraph agent workflows that plan steps, call tools, and verify their own output, removing hours of repetitive manual work.
  • Unlock privacy-sensitive enterprise deals by running open-source models (Llama 3, Mistral) fully in-house on client-owned infrastructure, keeping all client data off external APIs.

Systems Automation Engineer

Sodexo | Aug 2024 – May 2025

  • Saved 10+ hours of manual work every week by automating system health checks and daily status reporting with scheduled Python and PowerShell scripts across the campus kiosk and POS hardware fleet.
  • Reduced campus kiosk downtime 15% by analyzing peak-usage logs and shifting the team from reactive break-fix repairs to proactive, scheduled maintenance ahead of high-traffic windows.

Backend Software Engineer

Tata Consultancy Services (TCS) | Aug 2021 – Jul 2023

  • Cut manual ticket-sorting time 40% for a Fortune 500 client by integrating an ML text-classification model into their IT support system through Python (FastAPI) REST APIs.
  • Improved mission-critical client workflow performance 60% by profiling and optimizing PostgreSQL queries, adding targeted indexes, and rewriting inefficient backend data pipelines.
  • Cut deployment failures 30% and held code coverage above 85% by building thorough PyTest unit-test suites and enforcing CI/CD best practices on every release.

Projects

Aadyon Assist — Open-Source AI Life-Ops Platform

github.com/chiranjeevigundu/aadyon-assist (MIT)

  • Architected and open-sourced a self-hosted, multi-user AI platform end to end — data model, agent layer, ingestion, REST API, and iPhone app — as seven Docker Compose microservices on FastAPI and Postgres 16 with pgvector.
  • Designed a multi-agent organization where a CEO agent decomposes goals and delegates to four specialist agent teams, with explicit step limits and a full audit trail.
  • Engineered a human-in-the-loop safety model: read-only analysis runs autonomously, while any real-world side effect (money, email) becomes a proposal the user must approve.
  • Built a tiered model-routing layer over LiteLLM (OpenRouter, GPT-4o-mini, local Llama 3 via Ollama) driven entirely by a database table.
  • Designed multi-tenant isolation with Postgres Row-Level Security, JWT authentication, and Fernet-encrypted credentials.
  • Shipped solo with 149 automated tests, GitHub Actions CI, and ingestion pipelines that turn emails, PDFs, and bank transactions into reviewable to-dos via LLM extraction and OpenAI Vision.
FastAPIPostgres + pgvectorLiteLLMDocker ComposeOllama

Technical Skills

Languages & ML

PythonSQLJavaScriptTypeScriptBashPyTorchScikit-learnText Classification

AI / LLM

OpenAI APILangChainLangGraphCrewAIHugging FaceRAGAgentsPrompt EngineeringFine-Tuning (LoRA, QLoRA)OllamaLiteLLMGuardrails AIEmbeddingsSemantic SearchAgentic IDEs

Backend & Data

FastAPIREST APIsNode.jsPostgreSQLRedisPineconepgvectorMicroservicesReact

Cloud & DevOps

AWS (EC2, S3, Lambda, ECS)AzureDockerGitHub ActionsCI/CDGitPyTestAgile/Scrum