Pruthvi Garlapati
SENIOR GCP DEVOPS ENGINEER - UKG
Pruthvi Garlapati.

Platforms that
Run Themselves.

Senior GCP DevOps Engineer at UKG. I build cloud platforms for a living, and AI agent systems that have to show their work as proof of craft.

View My Work -> See on GitHub
Pruthvi Garlapati
Pruthvi Garlapati
Available for new opportunities - Senior GCP / Platform roles
INTERACTIVE

Drag to rotate, tap a node to inspect it - or scroll on for the guided tour.

Sach

Live WhatsApp-forward fact-checker. Paste a forward, get a cited TRUE / FALSE / MISLEADING / UNVERIFIED verdict.

79-claim evaluation - 0 overclaimed verdicts
About

I am a Senior GCP DevOps Engineer at UKG, building cloud platform infrastructure since 2018 - currently on the UTM infrastructure team, working on GKE platforms, a SQL Server 2022 migration, and PagerDuty noise reduction. Based between Hyderabad and Toronto, Canadian permanent resident.

In parallel I design and ship AI agent systems end to end, solo: a public-interest fact-checker used from WhatsApp, an autonomous options-research agent, and a live paper-trading desk. One rule runs through all of them: every claim an agent makes must be traceable to evidence, and "I could not verify this" is a valid answer.

8+
YEARS IN INFRASTRUCTURE, SINCE 2018
3
AI SYSTEMS LIVE IN PRODUCTION
0
OVERCLAIMED VERDICTS IN SACH'S 79-CLAIM EVAL
Flagship work
Live product - Code for a Billion, Governance
79Claims evaluated
0Overclaimed verdicts
$0Running cost

Sach - WhatsApp forward fact-checker ↗

Paste a viral WhatsApp forward and get a cited TRUE / FALSE / MISLEADING / UNVERIFIED verdict from PIB Fact Check and official sources, in English and 15 Indian languages, as a card ready to post back into the family group. Built solo, runs on free tiers, filed as submission #126.

AI agentsEvidence groundingFact-check APIsVercel
Problem

A viral forward reaches a family group in seconds; a human fact-check takes days. By then it has been believed, forwarded and acted on.

Architecture

A three-layer cascade: match the claim against PIB Fact Check's archive and published fact-checks first, then a live AI check grounded in official sources, and if the evidence is not there, an honest UNVERIFIED with a human tipline handoff - never a guess dressed as a verdict.

Outcome

Public 79-claim evaluation with zero overclaimed FALSE verdicts, abstention preferred over guessing. Live at sachcheck.in in English and 15 Indian languages, filed in the Code for a Billion judging window.

Proof

79 claims - 0 overclaimed FALSE - live at sachcheck.in

Sample session
Open Agent Hackathon 2026 - Track 02
252 of 547Screening rank
12.5 / 15Demo score
12Names per run

QuantPilot - research agent that shows its work ↗

An autonomous pre-market options research agent for US markets. It investigates 12 names across fragmented sources and produces trade cards where every number traces to the evidence packet it came from - including a verifier that catches the model misquoting its own data. Screening rank 252 of 547; demo score 12.5 of 15.

Multi-agent systemsCitation verificationPythonEval design
Problem

Research agents sound certain while misquoting their own data - and a trade idea built on a wrong number is worse than no idea at all.

Architecture

A multi-agent pipeline investigates 12 names across fragmented sources and assembles evidence packets. Every number on a trade card must trace back to its packet, and a separate verifier pass exists to catch the model misquoting its own evidence.

Outcome

Open Agent Hackathon 2026: screening rank 252 of 547, with a demo score of 12.5 of 15 - higher than all three Track 02 winners' demos (12.3 each).

Proof

Rank 252 of 547 - demo 12.5 of 15, above all three Track 02 winners

Sample session
Live system - paper trading only
5 minRefresh in session
0Real orders placed
100%Paper money

Cluse - autonomous paper-trading desk ↗

A Nasdaq-100 options research desk running on virtual money: technical setups, an intraday news radar, market-regime filters, and strict risk rules with a drawdown kill-switch. The public page refreshes every 5 minutes in session, with an interactive 3D diagram of the whole system.

Trading systemsRisk enginesDiscord botsThree.js
Problem

Strategy ideas are cheap. The hard part is a desk that sizes positions, takes profit, stops out and flattens by rule - proven without risking real capital.

Architecture

Nasdaq-100 technical setups pass through an intraday news radar and market-regime filters into a risk engine with conviction sizing, take-profit and stop-loss rules and a drawdown kill-switch. Everything flattens at the close; paper money only, by design.

Outcome

Runs in public as a live desk: refreshes every 5 minutes in session and republishes itself daily, with every position and exit on the page.

Proof

Live desk - 5-minute refresh in session - 0 real orders

Sample session
The lab

Three tiny canvas toys - the kind of play that keeps the serious work sharp. All three run on one shared animation loop and pause off-screen.

Lab 01 - Constellation - move your cursor through it
Lab 02 - Wave field - two sources, one interference
Lab 03 - Orbit sandbox - click to drop a body
Experience
JUL 2023 - PRESENT · TORONTO / HYDERABAD

Senior GCP DevOps Engineer · UKG

UTM infrastructure team: GKE and Cloud Run platforms, Terraform/OpenTofu with Terragrunt, Argo CD GitOps, SQL Server 2022 migration, PagerDuty noise reduction, FinOps with Kubecost and Spot VMs.

DEC 2020 - JUL 2023 · TORONTO (CONTRACT)

DevOps Engineer · TD Bank

Cloud and CI/CD engineering in a regulated banking environment.

SEP 2019 - DEC 2020 · HYDERABAD

DevOps Engineer · Stibo Systems

Release and infrastructure engineering for enterprise software.

JUL 2018 - SEP 2019 · HYDERABAD

Linux Administrator · Guidewire

Linux systems administration - where the infrastructure career started.

Education
2022

Postgraduate Diploma, Cloud Computing · George Brown College

One-year postgraduate diploma, completed while working full-time in DevOps.

2021

Postgraduate Diploma, Business Analytics · Cambrian College

One-year postgraduate diploma, completed alongside the George Brown diploma.

2014 - 2018 · HYDERABAD

BTech, Civil Engineering · CVR College of Engineering

Bachelor of Technology - the engineering foundation before the move into infrastructure.

Writing

Build notes from the two solo systems - the honest versions, numbers included.

Sach - fact-checking

Every family WhatsApp group in India has the same problem

Why I built a fact-checker that has to cite its verdicts, and what its 79-claim evaluation actually showed. Read on dev.to - the launch post on LinkedIn.

QuantPilot - agent evaluation

What a 66.5 out of 100 taught me

The QuantPilot build story from the Open Agent Hackathon: a demo that outscored all three track winners, and the innovation gap that kept it out of the finals. Read on dev.to - the original on LinkedIn.

Expertise

Cloud platform - GCP

  • GKE, Cloud Run, Cloud SQL / Spanner / Storage
  • Shared VPC, Private Service Connect
  • IAM and Workload Identity Federation

Infrastructure as code

  • Terraform / OpenTofu with Terragrunt
  • Argo CD GitOps, Helm, Kustomize
  • Cloud Build / Cloud Deploy

Reliability and FinOps

  • Cloud Monitoring, Prometheus, Grafana
  • PagerDuty incident practice
  • Kubecost, Spot VM strategy

AI agent systems

  • Multi-agent research pipelines
  • Evidence grounding and citation checks
  • Eval sets and red-team fixtures

Certifications: Google Cloud Professional Cloud DevOps Engineer - PagerDuty Foundational Practitioner.
Education: BTech, CVR College of Engineering, Hyderabad - PG diplomas in Cloud Computing (George Brown) and Business Analytics (Cambrian).

Contact