Systems Online

Artificial Intelligence × Engineering

BUILD
SMARTER.

Exploring the frontier where AI meets production systems. From LLM integration to Gen AI workflows — building intelligence into products that serve at scale.

Explore Work ← Portfolio
0
M+ Monthly Views
0
M+ Unique Users
0
+ Years Building
0
AI Integrations Shipped

What I build
with AI.

LLM Integration

Connecting large language models to real production systems. Prompt engineering, context management, and reliable output parsing for user-facing features.

OpenAI API LLM Prompt Eng. RAG

AI Content Intelligence

Automated summarization, intelligent content recommendations, and AI-assisted editorial modules — shipped at scale on platforms with 69M+ users.

Auto Summarization Recommendations Gen AI

GenAI Workflows

End-to-end generative AI pipelines for content automation. Building REST-based AI services and agentic workflows that integrate cleanly into existing stacks.

GenAI Workflows REST AI Services Automation

AI at Scale

Deploying AI features in high-traffic production environments without performance regression. Optimized hydration, edge caching, and smart lazy-loading for AI modules.

High-Traffic Arch. SSR Edge Caching Next.js

IoT × AI Dashboards

Real-time data prioritization and intelligent monitoring dashboards for healthcare IoT platforms. Thousands of concurrent device records, rendered with zero lag.

IoT Real-time React Node.js

SDK Engineering

Built and published the hindustan times.js SDK — enabling third-party platforms to embed real-time AI-powered news feeds. Designed for developer ergonomics and reliability.

SDK Design TypeScript NPM API Design
sk@ai-lab ~ integration-log
npm run ai:integrate --platform=livehindustan
✔ LLM pipeline initialized
✔ Context window: 128k tokens
✔ Auto-summarization module loaded
✔ Recommendation engine: online

deploy --env=production --users=69M
⟳ Running Core Web Vitals check...
✔ LCP: 1.2s CLS: 0.02 FID: 18ms
✔ Lighthouse score: 98
⚡ AI modules lazy-loaded at edge
✔ Deployment successful → 300M monthly views

OpenAI API LLM Integration Next.js React TypeScript Prompt Engineering GenAI Workflows Node.js SSR / ISR Core Web Vitals Edge Caching REST AI Services IoT Dashboards Firebase Docker AWSOpenAI API LLM Integration Next.js React TypeScript Prompt Engineering GenAI Workflows Node.js SSR / ISR Core Web Vitals Edge Caching REST AI Services IoT Dashboards Firebase Docker AWS

AI in the
wild.

001
HindustanTimes.com — AI Content Layer
Integrated AI-powered automated summarization, intelligent content recommendations, and AI-assisted editorial modules into a platform serving millions of daily active users.
OpenAINext.jsSSRTypeScript
002
LiveHindustan.com — Performance Migration
Led full migration to Next.js SSR + ISR architecture. AI-aware caching strategies, edge-rendered content modules for 69M+ unique users and 300M+ monthly page views.
Next.js ISRHydrationCode SplittingGenAI
003
Anelto — IoT Healthcare AI Dashboard
Real-time patient monitoring system with AI-driven data prioritization logic. Handles thousands of concurrent IoT device records with intelligent alerting and anomaly detection.
IoTReactReal-timeNode.js
004
hindustan times.js SDK
Published SDK enabling third-party platforms to embed real-time AI-powered news feeds. Designed for developer-first experience with clean APIs and minimal bundle footprint.
SDKTypeScriptNPMReal-time Feeds

AI should be
invisible to users
and invaluable
to the product.

The best AI integrations aren't flashy demos — they're seamless systems that make a product measurably better. Faster content discovery. Smarter recommendations. Zero added latency.

Building AI at the scale of Hindustan Times taught me that intelligence needs to be engineered with the same rigor as the underlying infrastructure. Performance is non-negotiable, even when you're running models at the edge.

Every feature I ship starts with a question: does this make the user's experience genuinely better? If the answer is yes, the engineering challenge becomes how to do it invisibly and reliably at millions of requests per day.

Open to Collaboration

Got an AI problem
worth solving?

suboork100@gmail.com