Arun Chukkala
Open to work

Portfolio — 2026 / San Francisco, CA

Applied AIEngineer

I'm Arun Kumar Chukkala. I design and ship production LLM systems — agentic workflows, retrieval, evaluation harnesses, and the guardrails that make AI safe to put in front of real users.

View work Résumé
Currently
Applied AI Engineer, IBM
Focus
LLM systems · Agents · Evals
Education
M.S. Computer Science
(01)

Selected work

01Startup — AI Retail Operations Platform

Cork

A production multi-tenant platform for independent stores — point-of-sale, inventory, purchasing, invoicing, payments, and loyalty in one system. Its AI layer turns paper distributor invoices into inventory updates, with human-in-the-loop confirmation so AI never writes to the books unverified.

  • Invoice intelligence — Gemini OCR → structured extraction → five-stage matching cascade; human corrections become learned aliases, so matching improves without retraining.
  • Evaluation-gated AI — an offline eval harness over real invoices holds the matcher at zero false positives, enforced as regression tests that block releases.
  • Production discipline — per-tenant isolation verified by tests, idempotent financial writes, integer-cent money math, audit trails, and per-tenant AI cost caps.
TypeScriptReactNode.jsPostgreSQLPrismapgvectorGemini
View live
02AI Medical-Bill Auditor

Claim Guardian

A free AI second opinion on any medical bill: reads a photo or PDF, prices every charge against real CMS Medicare rates, flags the overcharges, and drafts a cited dispute letter in ~60 seconds. Pricing is deterministic — the model explains findings but never invents a number.

FastAPIGeminiRAGNext.js
View live
03AI Job Search · LLM Evals

Agentception

Reads your resume, pulls live roles straight from applicant tracking systems, ranks them against you, and names the exact skills you are missing. Every claim is measured — an LLM eval harness over 69 real job descriptions (match AUROC 0.702, p = 0.017) that caught five bugs already shipped to production.

FastAPIReactVoyageSupabase
View live
04Multi-Agent Code Verification

Code Tribunal

A multi-agent AI court that checks whether AI-generated code did what the ticket asked. Seven agents cross-examine every diff — hunting missing requirements and scope creep — and stamp a deterministic 0–100 trust score you can gate CI on. Ships as a web War Room, a CLI, and an MCP server.

PythonFastAPIMCPNext.js
View live
05Compliance-Grade Financial RAG

FinAgent

A self-hosted research copilot for firms that ban public AI tools: six LangGraph agents run hybrid retrieval (BM25 + dense embeddings) over SEC filings, and a validator loops back on unsupported claims. Every answer is sealed into a SHA-256 hash-chained audit trail with an egress receipt naming exactly which providers touched the query — at ~$0.0005 per query.

PythonLangGraphQdrantNext.js

Production numbers / not demo numbers

62%

Agent latency reduction — 850ms to 320ms via async execution + semantic caching

30%

Manual review time cut with evaluation infrastructure and regression gates

98%+

Uptime on production LLM services with retry, timeout, and fallback handling

0

False positives on a 25-document evaluation harness, enforced by 15 regression tests

(02)

Experience

Mar 2024 — PresentUnited States

IBM

Applied AI Engineer

  • 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.
  • 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.
Jan 2021 — Dec 2022Hyderabad, India

Infosys

Software Engineer, Applied AI / Risk Platform

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

Education

M.S. Computer ScienceLamar UniversityDec 2024
B.Tech. Computer ScienceSri Indu Institute of Engineering & TechnologyMay 2020
(03)

Capabilities

AI / LLM Systems

  • Agent loops & tool calling
  • Retrieval-Augmented Generation
  • Embeddings & vector search
  • Evaluation harnesses & golden datasets
  • Guardrails & grounded refusal
  • Human-in-the-loop design
  • Semantic caching
  • LLM observability & tracing
  • OCR / document intelligence
  • LangGraph

Agentic Development

  • Claude Code
  • Cursor
  • Codex
  • Model Context Protocol (MCP)
  • Multi-agent code review
  • AI skills & internal tooling

Engineering

  • Python
  • TypeScript
  • FastAPI
  • Node.js / Express
  • React
  • PostgreSQL / Prisma
  • Docker & CI/CD
  • Vercel / Render / Supabase
  • Sentry
  • Azure
(04)

Research