Sanket Jivtode.

Hi, I'm Sanket Jivtode — Based in Bengaluru, India

I architected the frontend
for a national-scale AI platform
serving 2M+ users.

From LLM orchestration to pixel-perfect UI

I build the interfaces where AI meets real users. 7+ years delivering accessible, high-performance React architectures and Python orchestration layers across 5+ complex industries.

Read the Sahabat-AI case study →
LinkedIn Medium GitHub
2M+ Platform Users — Sahabat-AI
99.9% System Uptime — Healthcare
30% Velocity Boost — Team Lead
35% Smaller Bundles — Component Library
85%+ Test Coverage — All Projects
5+ Engineers Mentored

Featured Case Study

Sahabat-AI by Indosat

Indonesia's first national-scale AI platform — a 70-billion parameter open-source LLM serving 2M+ users across 5 languages, backed by one of the country's largest telecoms.

Context

Sahabat-AI is a sovereign AI initiative by Indosat Ooredoo Hutchison (~100M subscribers) in partnership with GoTo Group, AI Singapore, Google, and Nvidia. The platform supports Bahasa Indonesia plus 4 regional languages (Javanese, Sundanese, Balinese, Bataknese) — keeping the model, data, and infrastructure within national boundaries.

Launched at Indonesia's National Museum with government endorsement and covered by Fortune Asia →
The consumer-facing chatbot is live at chat.sahabat-ai.com.

My Role

Led frontend delivery and built the Python orchestration layer connecting the React UI to the model routing infrastructure. Deployed on-site in Indonesia for stakeholder discovery with Indosat's product and engineering teams.

  • • Built the LLM orchestration layer in Python — the middleware handling request routing, response streaming, and model-switching logic between the React frontend and the model routing infrastructure.
  • • Architected high-performance React interfaces for RAG workflows — the chat UI, conversation management, and response rendering that users interact with at chat.sahabat-ai.com.
  • • On-site stakeholder discovery — flew to Indonesia for requirements gathering with Indosat's product and engineering teams.

Technical Challenges

Multi-model traffic balancing

The platform routes between Sahabat's homegrown 70B model and frontier model fallbacks. The orchestration layer abstracts model-switching so the frontend renders responses identically regardless of which model generated them.

Streaming LLM responses

Chat interfaces must render token-by-token as the model generates. Built streaming response handling that maintains smooth UI rendering without blocking the main thread, even on lower-end Android devices common in Indonesia.

Low-bandwidth optimization

Indosat's 100M+ subscriber base includes users on 3G mobile connections across the Indonesian archipelago. Every interface decision — bundle size, API payload compression, progressive loading — was shaped by network reality, not lab conditions.

Multilingual UI

Supporting Bahasa Indonesia plus 4 regional languages with proper text rendering, input handling, and locale-aware layout patterns.

Architecture

User Input React Frontend API Gateway Orchestration Layer (Python) Model Router Sahabat LLM (70B, homegrown) Frontier Model (fallback) Response Stream

User requests flow through the React frontend to the orchestration layer, which routes to either Sahabat's homegrown 70B model or a frontier model fallback. Responses stream back token-by-token for real-time UI rendering.

Outcomes

2M+ Platform Users
70B Parameters
5 Languages
100M+ Indosat Subscribers

Covered by Fortune Asia. Endorsed by Indonesian government ministers at the national launch. Partnership ecosystem includes GoTo Group, AI Singapore, Google, and Nvidia.

Try it live → chat.sahabat-ai.com

Enterprise Impact

Due to NDA constraints, project details are anonymized. The technical challenges and outcomes are real.

Telecom Healthcare Banking Government Semiconductor Media / Streaming Trading
Healthcare

Accessible Patient Platform

A major healthcare organization needed a patient-facing platform that met strict WCAG 2.1 AA accessibility requirements while serving 100K+ users. I led the frontend implementation with a component architecture where every interactive element was built accessible-first — ARIA roles, keyboard navigation, and screen reader support tested at the component level, not the page level. Mentored 5 engineers on accessibility patterns, improving sprint velocity by 25%.

99.9% uptime
Banking

Payment Gateway Redesign

A Fortune 100 banking client needed a complete redesign of their payment gateway UI — every pixel has compliance implications and every interaction carries financial liability. I led the frontend redesign within PCI DSS constraints dictating input masking, session management, and data handling. The architecture prioritized progressive enhancement — if JavaScript failed to load, the payment flow still worked.

+15% engagement
Semiconductor

ML Annotation Tool

A major semiconductor company needed internal tooling for labeling and tagging datasets used in ML training pipelines. I built the annotation interface — a data-dense, high-interaction tool where annotators spend 8+ hours daily. The design focused on keyboard-first workflows, minimal context-switching, and batch operations that reduced per-annotation time. Enterprise internal tooling where the UX challenge is efficiency, not discoverability.

-40% per-annotation cycle
Government

New York State POC

Through Accenture's government consulting practice, I developed a proof-of-concept application for New York State/City government. Public-sector work operates under constraints commercial projects don't face — Section 508 accessibility mandates, specific security requirements, and stakeholder review cycles that add weeks to every decision. Navigated those constraints to deliver a functional POC that secured stakeholder approval to proceed to full implementation.

Approved for production
Media / Streaming

Video Streaming Platform

A media company needed frontend modules for their video streaming platform — content discovery UIs, playback controls, and adaptive streaming interfaces. The technical challenge was building UIs that respond to variable network conditions in real time: adjusting stream quality indicators, preloading content based on user behavior, and rendering media-heavy layouts without blocking core interactivity. Optimized for CDN-aware asset loading and service worker caching.

<2s time-to-first-frame

Side Projects & Open Source

Technical experiments and developer tools built outside of client work.

VS Code Extension

SimpleSync

A technical experiment in peer-to-peer architecture — real-time LAN file synchronization for VS Code using WebSocket and mDNS discovery. Built to explore P2P patterns and offline-first networking, not as a flagship product.

View on Marketplace
Developer Tools

CodeUtils

55+ developer utilities with a privacy-first, client-side-only architecture. No server, no tracking, no accounts. Every computation runs in the browser — data privacy guaranteed by architecture, not policy.

Visit Live App
Data Visualization

SimpleViz

CSV/Excel/JSON chart maker where 100% of processing happens client-side. Designed for teams handling sensitive data who can't risk uploading to third-party services. Privacy guaranteed by architecture — zero network requests for data.

Visit Live App

How I think about Systems

The network is hostile

Every interface I build assumes 3G speeds and intermittent connectivity. Building Sahabat-AI for Indonesian mobile users on varied networks taught me that performance isn't a feature — it's the feature. If your AI product takes 8 seconds to render a response, users don't care how smart the model is.

Accessibility is architecture, not a checklist

WCAG compliance can't be bolted on after launch. On the healthcare platform, accessibility was the load-bearing wall — 100K+ users with varying abilities depended on it. I treat ARIA roles, keyboard navigation, and screen reader support as architectural decisions, not QA tickets.

The best orchestration layer is invisible

On Sahabat-AI, we swapped underlying LLM models mid-sprint. The frontend needed minimal changes — a configuration update, not a rewrite. That's the test: if your orchestration is well-abstracted, the team shipping UI shouldn't need to know or care which model is running underneath. Good infrastructure makes itself invisible.

Technical Depth & Breadth

Frontend Core

7+ years

  • React Component architecture, custom hooks, compound patterns, performance profiling
  • Next.js SSR, ISR, App Router
  • TypeScript Strict mode, generics, discriminated unions, type-safe API layers
  • Tailwind CSS
  • Redux Toolkit

AI / LLM

Production systems

  • LLM Orchestration Multi-model routing, response streaming
  • RAG Pipeline Interfaces
  • LangChain
  • Prompt Engineering Production UIs

Backend

 

  • Python FastAPI, LangChain, RAG pipelines
  • Node.js
  • Express
  • REST API Design

Infrastructure

 

  • GCP
  • AWS (S3, CloudFront)
  • Docker
  • CI/CD Pipelines

Testing

85%+ coverage standard

  • Jest
  • React Testing Library
  • Vitest
  • Cypress
  • Playwright

Accessibility

 

  • WCAG 2.1 AA/AAA
  • ARIA Patterns
  • Screen Reader Testing
  • Keyboard Navigation
  • Focus Management

7+ years across 3 companies

05/2024 — Present

Quantiphi Analytics

Senior Software Engineer 2

Leading frontend architecture for enterprise AI and healthcare products at scale.

  • • Led end-to-end delivery of an AI application for Indosat (Indonesia), from on-site stakeholder discovery through production launch for a platform serving 2M+ users.
  • • Architected LLM orchestration layer in Python and built high-performance React interfaces for RAG workflows, connecting AI pipelines to intuitive user experiences.
  • • Shipped WCAG 2.1 AA-compliant healthcare platform for 100K+ users with 99.9% uptime. Mentored 5 engineers, improving sprint velocity by 25%.
09/2021 — 04/2024

Accenture

Custom Software Development Analyst

Shipped component libraries and performance-optimized UIs across enterprise client engagements.

  • • Built comprehensive component library with 50+ reusable React components leveraging hooks, custom hooks, and compound component patterns, reducing development time by 30%.
  • • Redesigned payment gateway UI from the ground up, increasing user engagement by 15%. Maintained 85%+ code coverage across all projects.
  • • Optimized frontend performance — 35% reduction in bundle sizes through code splitting, lazy loading, and tree-shaking, improving Core Web Vitals across all client projects.
09/2019 — 08/2021

Applied Cloud Computing

UI Developer

High-performance web applications using React and Next.js.

  • • Built and optimized UI components and frontend APIs, improving application load times by 40% through performance profiling and optimization.
  • • Implemented state management solutions using Redux and Context API for complex application workflows.
  • • Integrated RESTful APIs and handled asynchronous data flows with modern patterns (React Query, SWR).

Recent Writing

Vibe Coding: UI Design Architecture That Actually Feels Right

READ (5 MIN)

Exploring how to build user interfaces that go beyond highly functional and actually feel right through architectural patterns.

The Cost of Javascript

READ

Analyzing the impact of bundle size on time-to-interactive in emerging markets.

What colleagues say

Sanket is a phenomenal UI expert who also possesses a deep understanding of backend architecture. His ability to anticipate how frontend decisions impact backend scalability is rare and invaluable.

Suman Nunia

Engineering Manager, Quantiphi Analytics

The modular component systems he architected saved us months of technical debt. He doesn't just build beautiful interfaces; he builds full-stack systems that are robust and incredibly fast.

Sanket seamlessly bridges the frontend-backend divide. His optimizations improved our app's performance by 40%, and his mentorship elevated the entire team's engineering standards.