Retail agents · Connected workflows

AI, closer to the work.

arun7.com

Arun Chukkala

AI Implementation Engineer · Retail agents & operational AI · Building Cork

San Francisco, CAContact info

IBM Lamar University

Email me Résumé

Open to thoughtful work

AI implementation roles and collaborations, in San Francisco and beyond.

LinkedIn is temporarily unavailable. This is my personal profile on arun7.com.

About

I turn AI into useful, dependable tools for the people doing the work. My focus is retail agents and connected workflows: less re-entry, fewer loose ends, and more room to run the business.

I’m building Cork to bring checkout, inventory, purchasing, and invoices into one connected system for independent retailers. The AI handles repetitive steps, while the store team stays in control of the decisions that matter.

My enterprise work at IBM centers on agent workflows, evaluation, and the engineering that makes AI reliable in practice. I care about the full implementation: the data, the integrations, the way failures are handled, and how a team will operate the system after the demo.

Current focusRetail operations · Invoice intelligence · Dependable agents

Featured

Product · Retail operations

Cork

Connected checkout, inventory, and invoices, with retail agents that take care of the repetitive steps.

Explore Cork

ResearchBARC: Blast-Radius-Aware Agentic Control PDF

Experience

AI implementation & agent systems

IBM

Mar 2024 — Present

United States

Design and maintain evaluation infrastructure for LangGraph-based agent workflows in a regulated enterprise environment — golden datasets, regression gates, human-in-the-loop review — reducing manual review time by 30%.
Reduced agent workflow latency by 62% (850ms → 320ms) through asynchronous execution and semantic caching of LLM calls.

Show more at IBMShow less

Ship Dockerized Python/FastAPI services orchestrating LLMs, internal tools, and enterprise data through CI/CD — 98%+ uptime with retry, timeout, and fallback handling around non-deterministic model calls.
Build production observability that traces agent execution, tool calls, and failure modes end to end, converting production failures into permanent regression tests.

Software Engineer, Applied AI / Risk Platform

Infosys

Jan 2021 — Dec 2022

Hyderabad, India

Engineered ensemble anomaly-detection workflows for fraud decisioning, reducing false positives by 18% on a regulated risk platform.
Designed and deployed Dockerized FastAPI microservices and Azure Data Factory ETL pipelines processing 15M+ records.

Show more at InfosysShow less

Implemented output-consistency monitoring that alerted on model drift before it reached downstream decisions.

Education

Lamar University

M.S. Computer Science

Dec 2024

Sri Indu Institute of Engineering & Technology

B.Tech. Computer Science

May 2020

Projects

Cork

Product & engineering · Retail agents & operations

Independent retailers have enough to keep track of. I’m building Cork to connect checkout, inventory, purchasing, and invoices, with retail agents that handle the repetitive steps and leave the important decisions with the store team.

TypeScript · React · Node.js · PostgreSQL · Prisma · pgvector · Gemini

Aptly Wallet

Explainable card recommendations · Consumer product

I built Aptly Wallet to help people choose which of their existing cards to use for a purchase. A deterministic TypeScript engine compares reward rules and purchase conditions, then explains the rate and estimated value behind its recommendation. Alongside the web app, I built a Chrome extension.

TypeScript · React Native · Expo · Chrome MV3 · Supabase

Show 4 more projectsShow less

Claim Guardian

AI Medical-Bill Auditor

Turns a medical bill into a review of its charges, using CMS rate references and cited explanations. Calculations stay in code; the model helps make the findings understandable.

FastAPI · Gemini · RAG · Next.js

Agentception

AI Job Search · LLM Evals

Matches a résumé against live roles and explains where the fit is strong or incomplete. An evaluation harness checks the ranking against real job descriptions.

FastAPI · React · Voyage · Supabase

Code Tribunal

Multi-Agent Code Verification

Checks code changes against the original requirements, using multiple agents to surface omissions and scope changes. Available through a web interface, CLI, and MCP server.

Python · FastAPI · MCP · Next.js

FinAgent

Compliance-Grade Financial RAG

A self-hosted research workflow over SEC filings. Combines retrieval, source validation, and an audit trail so teams can inspect how an answer was produced.

Python · LangGraph · Qdrant · Next.js

Skills

AI implementation
Retail agent workflows
Document intelligence / OCR
Human-in-the-loop design
Evaluation & guardrails
LangGraph
Retrieval & tool calling
Model Context Protocol (MCP)

Show all 16 skillsShow less

Python
TypeScript
React
FastAPI
Node.js
PostgreSQL / Prisma
Docker & CI/CD
Tracing & cost controls