Hello, I'm

Bill Klinten
Guduru

I'm a |

Software engineer who has designed and shipped 6 production AI agents and integrations in the past year — multi-agent RAG pipelines, autonomous QA agents, and conversational AI UX — on top of 6+ years shipping full-stack applications at Infosys/EdgeVerve.

BKG

Bill Klinten Guduru

AI Agent Developer & Full-Stack Engineer

0+ Years Exp
0+ Skills
0+ Projects
Spring Boot Node.js React AI Agents
Scroll Down

Know Me Better

I'm a Software Engineer with 6+ years of full-stack experience at EdgeVerve and Infosys. Over the past year I've designed and shipped 6 production AI agents and integrations — multi-agent RAG pipelines, autonomous QA and governance agents, and conversational AI UX — used by real engineering teams, not tutorials.

My AI work focuses on embedding intelligence into existing systems — not building demos. I design multi-agent RAG pipelines, LLM-powered middleware, and context-bounded assistants that operate inside real production constraints. AI as an integration layer, not a replacement.

Location Bengaluru, India
Experience 6+ Years

AI Agent & Integration Engineering

6 production AI agents & integrations shipped in the past year — multi-agent RAG pipelines (AI Canvas, Claude/Bedrock, PGVector), autonomous QA/governance agents, and conversational AI UX

Full Stack Development

Building end-to-end enterprise applications with React, Angular, and modern JavaScript frameworks

Backend Systems

Designing scalable APIs and microservices with Spring Boot, Node.js, and Express

AI as middleware, not magicSits between existing systems — reasoning, deciding, transforming — without replacing what already works
Constraint engineering firstEvery agent starts with what it must NOT do: no hallucination, no out-of-scope answers
Structured output, alwaysJSON schemas and validation on every AI call — parseable and predictable, never free-text guesswork

Work Experience

Current Role
2024 — Present

Member — UI Development

EdgeVerve Systems Limited

Bengaluru, India

  • Designed multi-agent RAG pipelines (DocViz AI, 5-Minute RCA Tool) on AI Canvas with Claude Sonnet 4.5 (Bedrock) + PGVector — turning documentation into narrated explainer videos and root-cause analysis reports
  • Built autonomous agents for documentation QA (Doc Portal Reviewer Agent — Playwright + LLM validation) and Copilot usage governance (Quota Smart Copilot — a custom VS Code agent)
  • Shipped AI Integration UX — a GenAI search overlay for an enterprise docs portal and the context-engineering layer behind a conversational banking UI that grounds every AI query in the user's real journey
  • Continued leading UI development across enterprise banking platforms and mentoring junior developers
AI Canvas Claude (Bedrock) RAG / PGVector React Node.js
Promotion
2022 — 2024

Product Engineer

EdgeVerve Systems Limited

Bengaluru, India

  • Developed and maintained enterprise product features for banking solutions
  • Built scalable UI components using Polymer.js and WaveMaker
  • Collaborated with cross-functional teams for product delivery
  • Implemented RESTful APIs using Spring Boot and Node.js
Spring Boot Polymer.js WaveMaker LoopBack
Promotion
2021 — 2022

Senior Systems Engineer

Infosys Limited

India

  • Promoted for outstanding performance and technical contributions
  • Took ownership of complex modules and feature development
  • Provided technical guidance to team members
  • Contributed to system design and architecture decisions
Java Spring Boot JavaScript Angular
Career Start
Dec 2019 — 2021

Systems Engineer

Infosys Limited

India

  • Started professional career in enterprise software development
  • Worked on full-stack development for client projects
  • Gained expertise in Java, Spring Boot, and front-end technologies
  • Delivered quality code with strong adherence to best practices
Java Spring Boot HTML/CSS JavaScript

Skills & Expertise

Organized by category. Each skill is tied to real production work — not self-assessed percentages.

AI Agent & Integration Engineering

Primary focus — applied in production and internal agent tooling

🤖 Multi-Agent Orchestration RAG pipelines with retriever, analyst, and validator agents (AI Canvas)
🔎 RAG & Vector Search PGVector collections tuned per use case
🔌 LLM API Integration Claude (Bedrock), Gemini, OpenAI-compatible APIs
🧠 Structured Output & Validation Zod / JSON schema enforcement with auto-repair pipelines
Agent Automation Playwright-driven QA agent, VS Code custom agents
📝 Prompt & Constraint Engineering Bounding LLM output to production-safe behavior

Full-Stack Development

Shipped in enterprise products, used by real clients

React.js Enterprise UI — Expense Management platform
Spring Boot Banking APIs — Cash Management, Payments
Node.js API middleware, SDK tooling, agent backends
TypeScript Used across newer frontend and agent modules
Java Spring Boot services for Finacle banking platform
🔗 REST APIs & Microservices Designed & consumed across all enterprise projects

Platforms & Tools

Working knowledge, used in production or agent tooling

Angular Payment Services frontend
Python AI agent backends, RCA tooling, doc QA automation
Docker Containerized agent deployments
AWS (S3, EC2, Bedrock) Claude Sonnet 4.5 via Bedrock; basic cloud deployments
Git / GitHub Version control across all projects, 6+ years

Projects

DocViz AI

Multi-Agent RAG + Video Generation

Built a 4-agent RAG pipeline (retriever → analyst → creative director → storyboard engineer, plus a QA validator) that turns enterprise documentation into narrated, animated explainer videos — with a from-scratch client-side animation and MP4 export engine.

Claude Sonnet 4.5 (Bedrock) PGVector React / TypeScript Zod

5-Minute RCA Tool

AI Root-Cause Analysis Agent

Built a zero-dependency Python agent that matches error signatures against curated playbooks and cross-references live GitHub code search across linked repos — turning a manual, multi-repo debugging routine into a single query.

Python GitHub Search API RAG React

Doc Portal Reviewer Agent

Autonomous Documentation QA

Authored an autonomous agent that crawls documentation portals with Playwright, validates every checklist item with an LLM, and generates a shareable HTML/JSON audit report with confidence-scored verdicts and evidence screenshots.

Python Playwright LLM Validation Confidence Scoring

Quota Smart Copilot

AI Usage Governor Agent

Designed a custom VS Code agent that classifies every request and routes it to the cheapest safe model tier based on remaining Copilot budget — keeping full agentic capability while enforcing cost discipline across the team.

VS Code Custom Agents TypeScript GitHub Copilot API

AI Doc Portal & Conversational Banking UI

GenAI UX + Context Engineering

Added a Google-AI-Overview-style GenAI answer experience to an enterprise MkDocs portal, and built the context-engineering layer behind a conversational banking UI — summarizing full user journeys into compact context sent with every AI query.

Vanilla JS MkDocs React / TypeScript Context Engineering

This Portfolio

Open Source — Live AI Playground

The site you're on right now — including 3 working AI agents (chat, resume fit analysis, code review) built with the same constraint-first, structured-output patterns used in production.

HTML / CSS / JS Gemini / Groq API Function Calling

Finacle Banking Platform

Cash Management · Expenses · Payments

Built full-stack UI and APIs across three Finacle banking modules — transaction tracking, expense approval workflows, and cross-border payment processing — serving 50+ enterprise banking clients.

Spring Boot React Angular Node.js

AI Playground

Three working agents built on this site — chat, resume fit analysis, and code review — all sharing the same constraint-first, structured-output patterns I use in production. View source on GitHub

Talk to My AI-Powered Resume Assistant

This chat uses Gemini's function-calling API with 4 custom tool definitions. The LLM decides which tools to invoke based on conversation context. My entire profile is injected as structured context — the same pattern I use for production SDK documentation assistants.

Technical Implementation

  • Gemini Function Calling LLM receives tool definitions and decides which to call — same pattern as my production SDK assistant
  • 4 Tool Definitions showLocationImage • showTechLogo • highlightSection • showProjectDetails — dispatched by the model, not by if/else logic
  • Structured Context Injection Profile data is converted to a structured text format and passed as system context — bounded to this data only
  • Constraint Engineering System prompt constrains responses to profile data only — the same hallucination prevention I apply in enterprise work
BKG AI Assistant Powered by Gemini

Paste a Job Description — Get an Honest Fit Analysis

This tool sends the job description along with my full profile to Gemini and requests a structured JSON response covering: skill matching, fit scoring, gap identification, and a tailored summary — the same structured-output pattern I use in production AI integrations.

JD + Profile
LLM Analysis
JSON Schema
Visual Results

Paste Any Code — Get a Structured Review

This agent demonstrates constraint-bounded AI and structured output enforcement. It's constrained to only review code, scores across 5 quality dimensions, and returns a strict JSON schema that the UI renders into visual results.

Constraint Engineering
Structured JSON Output
Multi-Dimensional Analysis
Language Auto-Detection

Academic Background

June 2015 — April 2019

Bachelor of Technology (B.Tech)

Electrical and Electronics Engineering

Sri Krishnadevaraya University

B.Tech

Contact Me

Let's Work Together

Feel free to reach out for collaborations, opportunities, or just a friendly conversation about technology and AI.

Based in Bengaluru, Karnataka, India
BKG AI Assistant Powered by Groq