Sathish Raja
Senior Full-Stack Engineer, Building Production AI Systems
14+ years shipping full-stack platforms across government, finance, and robotics in Singapore. Now building multi-agent AI systems with LangGraph, RAG, and MCP — most recently an AI hiring platform built solo, end to end.
Cut deployment errors 50% and lifted API throughput 40% on production robotics platforms at Konica Minolta · 10+ production apps shipped across 4 industries
👤 About
Who I Am
Sathish Raja · Singapore
Senior Software Engineer with 14+ years building full-stack platforms across government, finance, and robotics in Singapore — 10+ production applications shipped in total.
Most recently, I led the engineering on an Autonomous Mobile Robot platform suite at Konica Minolta, and I'm now building production multi-agent AI systems independently — including an AI hiring platform and a multi-agent AI code review platform, both designed and shipped solo, end to end.
I work across the full stack, from backend architecture and cloud deployment to the frontend, and now increasingly with AI-agent workflows layered on top of that same foundation.
Technologies
- Google Gemini
- LangGraph
- LangChain
- RAG
- MCP SDK
- Qdrant
- Ollama
- React / Next.js
- TypeScript
- Zustand
- TanStack Query
- Tailwind CSS
- Framer Motion
- Node.js / Express
- BullMQ
- Redis
- RESTful APIs
- Microservices
- MongoDB
- MySQL
- PostgreSQL
- Redis
- AWS (EC2, S3)
- Docker
- Vercel / Render
- Nginx
- CI/CD
- JWT
- Helmet
- Zod Validation
- Bcrypt
🛠️ Services
What I can build for your team or business.
Web Application Development
Full-stack web apps built with Node.js, React, and Next.js — from MVP to production scale.
Custom Website Development
Custom-built business and marketing websites, optimized for performance and SEO.
AI Chatbot Solutions
Conversational AI agents built with LangGraph and RAG, tailored to your data and workflows.
Workflow Automation
Background job pipelines and automation systems that remove manual, repetitive work.
API Development & Integration
RESTful and GraphQL APIs designed for reliability, plus integration with third-party systems.
AWS Cloud Deployment
Containerized deployments on AWS with Docker, CI/CD pipelines, and production monitoring.
MVP Development
Fast, focused builds to validate an idea before committing to a larger investment.
Technical Consulting
Architecture reviews, tech stack decisions, and hands-on guidance for engineering teams.
🤖 AI Solutions
Purpose-built AI systems for business processes — not just generic chat widgets.
AI Chatbots
Conversational agents wired to your own data and workflows, not just a generic FAQ bot.
Lead Generation Bots
Agents that qualify and route inbound leads automatically, before a human ever gets involved.
Customer Support Assistants
AI assistants that resolve common support questions and escalate the rest with full context.
AI Content Automation
Automated pipelines for generating and organizing content at scale, with a human review step.
Workflow Automation
Background agent pipelines that take over repetitive, multi-step business processes.
📦 Featured Projects
Pick a project below to see what it does, how it's built, and the impact it had.
SmartHireAI Platform
AI hiring platform that screens candidates automatically
↗ View Live// Project Scope Summary
A multi-tenant AI hiring platform I designed and built solo, with separate dashboards for candidates, recruiters, and hiring managers. Autonomous AI agents parse incoming resumes and rank candidates against role requirements, removing the manual first-pass screen recruiters normally do by hand.
// Integrated Stack Badges
Data Ingestion & Integration Topologies
Explicit engineering pathways mapped directly out of production system parameters.
LangGraph recruiter agent with human-in-the-loop approval
Qdrant Cloud: Gemini embeddings, job-filtered search
BullMQ / Redis jobs: PDF extraction, Gemini analysis, scoring
pdf2json / pdfjs-dist resume parsing pipeline
The AI Recruiter is orchestrated with LangGraph: it retrieves candidates, evaluates skills, experience and relevance, ranks recommendations, proposes actions, and pauses for human approval before any side effect happens (human-in-the-loop). Resumes are parsed with pdf2json and pdfjs-dist inside BullMQ and Redis background jobs that handle PDF extraction, Google Gemini profile analysis and scoring, so the API never blocks on AI work. Semantic matching uses Gemini embeddings in a Qdrant Cloud vector database with job-filtered search for job-specific candidate retrieval. Through the Model Context Protocol (MCP), agents can create, reschedule and cancel interviews and send candidate emails via Resend, with human approval and duplicate-interview protection. Access is secured with JWT authentication and role-based access control across candidate, admin, recruiter and hiring-manager dashboards.
💬 Client Testimonials
Available for freelance and contract opportunities.
💰 Pricing
Every project is scoped individually — reach out for a custom quote.
Starter Website
A focused marketing or portfolio site to get you online.
- ✓Custom design, mobile-first
- ✓Up to ~5 pages
- ✓Basic SEO setup
Business Website
A fuller business site with more content and integrations.
- ✓Multi-page site with CMS or blog
- ✓Contact/lead forms
- ✓SEO + performance optimization
Custom Web Application
A full-stack application built around your workflow.
- ✓Custom backend + database design
- ✓User accounts / dashboards
- ✓API integrations
AI Automation Solution
AI agents or automation wired into your business process.
- ✓AI chatbot or agent workflow
- ✓Workflow automation pipeline
- ✓Integration with your existing tools
🧭 How I Work
What working together actually looks like, step by step.
Discovery Call
A short call to understand what you're building and whether it's a fit.
Proposal & Scope
A clear scope, timeline, and quote — no surprises once work begins.
Build
Regular check-ins as the project progresses, not a black box until launch.
Launch
Deployed, tested, and handed over — or fully managed if you prefer.
Support
Ongoing support and iteration scoped separately, if you need it.
❓ Frequently Asked Questions
Ready to build your next project?
Reach out with what you're building — I'll get back to you to scope it out.