The Engineer's Gazette — Sai Arvind Krishnan

◆RAG latency cut 35% at SetuCS.io ◆Token costs down 40% via batched LLM calls ◆Telecom billing audit pipeline live · AT&T · Verizon ◆M.S. Software Engineering · Arizona State University · May 2026 ◆Java · Python · PostgreSQL · Azure · FAISS · Spring Boot ◆Technical Lead · ASU LX Design ◆

About the Engineer

Featured Profile · Arizona, USA

Backend Engineer Builds
Production Systems
From First Principles

Specialising in transactional backends, RAG pipelines, and SQL-heavy data architecture — with measurable, production-verified results across telecom, inventory, and ML-backed platforms.

Sai Arvind Krishnan is a backend-focused software engineer currently pursuing a Master of Science in Software Engineering at Arizona State University, where he serves as Technical Lead for the ASU LX Design programme.

His work spans on-premises Java inventory systems, cloud-deployed RAG platforms on Azure, and enterprise-grade telecom billing audit pipelines — each built with a consistent focus on correctness, performance, and operational observability.

Across four production systems, his changes have measurably moved the needle — P95 latency down 35%, token costs down 40%, query performance up 25%, and 40% of recurring manual effort automated away. Not targets, but shipped results.

↓ Download Résumé ⌥ View GitHub

Correspondence

✉ saiarvind2020@gmail.com
☏ +1 (623) 272-9142
⌂ Arizona, USA

On The Wire

⌥ github.com/SAI-ARVIND-KRISHNAN
⬡ linkedin.com/in/skris179

"Proven ability to optimise latency, token usage, and query efficiency — from architecture to production debugging." — Engineer's Summary

Career Dispatches

Current · Dallas TX (Remote)

SetuCS.io Sees 35% Latency Gains After RAG Overhaul

By Sai Arvind Krishnan · Software Engineering Intern · Aug 2025 – Present

Consolidated multiple Gemini LLM calls into single batched requests with ChromaDB vector retrieval, cutting P95 latency 35% and token costs 40% in Node.js/Express. Re-architected SQL schema to 3NF with composite indexes, improving multi-tenant query performance by 25%. Deployed on Azure VMs with NAT Gateway; Azure Monitor reduced mean time to detection 40%. Implemented JWT authentication with Casbin-based RBAC, cutting authorization defects 30%.

Node.jsRAGChromaDBAzureJWT/RBACReactTypeScript

Capstone · Tempe, AZ

TEOCO Audit Pipeline Now Processes AT&T & Verizon Invoices

By Sai Arvind Krishnan · Software Engineer · Jan 2026 – Present

Built Python PDF ingestion pipelines using pdfplumber and PyMuPDF, normalising carrier billing invoices into auditable PostgreSQL schemas. Implemented cross-document validation for overcharge detection. Added a FAISS-backed RAG layer enabling semantic evidence retrieval and human-in-the-loop reprocessing via Python APIs.

PythonPostgreSQLFAISSpdfplumberRAG

Industry · Chennai, India

Manufacturer Ditches Spreadsheets for Java Inventory Backend

By Sai Arvind Krishnan · SWE Intern · May – Dec 2023

Replaced spreadsheet-based vendor and inventory tracking at Inox Tools Ltd. with a Java 17 / Spring Boot backend modelling vendors, SKUs, purchase orders, and inventory ledgers in PostgreSQL. Automated batch jobs cut manual reconciliation by 40% weekly. Ledger-based transaction logic with idempotent updates eliminated double-counting during PO receipts and returns.

Java 17Spring BootPostgreSQLSpring Data JPAREST

Research · VIT, Chennai

Deep Learning RNN Achieves Semantic Audio Similarity Beyond DSP

By Sai Arvind Krishnan · Research Intern · Dec 2023 – May 2024

Built an end-to-end Music Information Retrieval pipeline using MFCC, Chroma STFT, and beat-synchronous embeddings for kNN similarity search. Designed and trained a pairwise RNN similarity model in TensorFlow/Keras. Productionised with PyTest, pickle artifact pipelines, and a modular CLI.

Pythonlibrosascikit-learnTensorFlowkNN

Technical Repertoire

Languages

Java · Python
TypeScript · JS
C++ · SQL · C#

AI & Data

RAG · LLM APIs
FAISS · Chroma
Embeddings
PostgreSQL · MongoDB

Backend & APIs

Spring Boot
Node.js · Express
ASP.NET Core
REST · GraphQL

Cloud & Infra

AWS (EC2, S3, RDS)
Azure VM · Monitor
Docker · CI/CD
Git · Agile

Academic Record

Graduate · Arizona, USA

Master of Science in Software Engineering

Arizona State University — Ira A. Fulton Schools of Engineering

Aug 2024 – May 2026 · Technical Lead, ASU LX Design

Undergraduate · India

B.Tech. Computer Science & Engineering

Vellore Institute of Technology, Chennai, India

Aug 2020 – May 2024 · Hackathon Finalist Nominee