cd /news/artificial-intelligence/meet-the-builder-why-i-m-in-for-coho… · home topics artificial-intelligence article
[ARTICLE · art-98959] src=dev.to ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

Meet The Builder: Why I'm In for Cohort 3

Mahajan Ashok, an AI product engineer and freelance full-stack developer based in Hyderabad, is joining Cohort 3 of the 'Accelerate AI with Cloud Run' program. Ashok, who runs Mahajan IT Solution and has built production systems for clients using React, Next.js, and AWS, aims to deepen his expertise in multi-agent orchestration and Cloud Run patterns for AI workloads. He plans to apply these skills to his freelance projects and connect with other builders in the APAC region.

read2 min views1 publishedAug 16, 2026

I'm Mahajan Ashok — AI Product Engineer, freelance full-stack dev, based out of Hyderabad. Fresh B.Tech CSE (Data Science) grad from TKR College, currently running my own freelance thing, Mahajan IT Solution, while job hunting on the side.

Quick backstory

Last year or so I've been building real stuff for real clients — not tutorials, actual production systems. Relicus (wellness/learning platform, live video + payments), a multi-vendor marketplace on native AWS, a few e-commerce builds, and an automation pipeline that posts to LinkedIn on autopilot with a human-approval step baked in. Stack's mostly React, Next.js, NestJS, FastAPI, MongoDB, Supabase, AWS. Picked up ~20 certs along the way too, including Oracle OCI GenAI Professional and Salesforce Agentforce Specialist.

Honestly what I keep gravitating toward is AI that does things, not just chats — agents wired into real tools and real data, actually moving work forward.

Why Cohort 3

"Accelerate AI with Cloud Run" is exactly my kind of learning — build-first, not another set of disconnected tutorials. One coffee shop, three labs, growing the whole time: personalized customer experience → location intelligence for expansion → automating ops to run leaner. All shipped on Cloud Run with Gemini, ADK, multi-agent orchestration.

That's basically how I work with freelance clients too — ship an MVP, layer in the intelligence, then optimize once it's actually running. Getting to do that on Google Cloud's AI-native stack, and learn how production multi-agent systems are actually supposed to be deployed, is exactly where I want to level up next.

What I'm here for

Actually understanding multi-agent orchestration, not just single-agent chatbots

Cloud Run patterns for AI workloads at scale

Taking what I learn straight into my own freelance/personal projects

Meeting other builders across APAC grinding on the same problems

Let's build.

LinkedIn: linkedin.com/in/mahajanashok78

GitHub: github.com/Mahajanashok2456

Portfolio: mahajanashok.in

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @mahajan ashok 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/meet-the-builder-why…] indexed:0 read:2min 2026-08-16 ·