Enterprise RAG HR AssistantRAGEnterprise RAG HR AssistantRetrieval-Augmented Generation assistant on Azure AI Foundry and Azure OpenAI that answers employee and leadership questions over internal HR data, with Pinecone vector search and role-aware prompt guardrails.RAGAzure AI FoundryAzure OpenAIPineconeHello! I Am Nishanthan Janarthanarajah
An Engineer who
Judges a book by its cover...
Because if the cover does not impress you what else can?
I'm an Associate Technical Lead.
Currently, I'm a Associate Technical Lead at Eight25Media.
Full Stack Developer and Engineering Lead with 7+ years architecting and delivering scalable, high-performance solutions across JavaScript/TypeScript, Next.js, React, Node.js, headless CMS, and cloud platforms. I lead cross-functional engineering teams end-to-end, from architecture through production, while aligning technical execution with business and marketing goals. I've scaled engineering teams from 6 to 31 engineers, directed enterprise B2B platform delivery, and built trusted client relationships, with deep experience in Next.js/Contentful/Vercel architecture, technical SEO, caching and performance engineering, CI/CD pipelines, and AWS.
I'm increasingly focused on applied Generative AI and LLM application engineering: designing production Retrieval-Augmented Generation (RAG) systems on Azure AI Foundry and Azure OpenAI with Pinecone vector search and role-aware prompt guardrails, and building Model Context Protocol (MCP) servers that let AI agents drive design-to-code generation and headless CMS content automation.
If you want to put AI agents to work in your business — agentic workflows, RAG assistants over your own data, MCP servers, or AI features inside your product — I'd love to talk about what you're building.
New product · live now
Meet Flows
“Describe the process. We run it.”
Flows is my own product: an agentic automation platform for small businesses and agencies. You describe a process in plain English, and Claude drafts the workflow, wires up your apps, runs it around the clock, and tells you in one sentence when something needs you.
- Plain English in, running workflow outNo canvas, no nodes, no field mapping by hand. Describe it like you'd brief a new hire.
- Claude repairs what breaksWhen a run fails, the agent reads the error and the data, explains it in one sentence, and offers the fix.
- Built for the tools small teams already useSlack, Google Sheets, Gmail, SMS and any REST API. One run is one task, however many steps.
Built withNext.jsClerkClaude APITailwind CSS
create-your-flows.nishy.space
Key Projects
Work that shipped, at scale
7 projects across AI agents, B2B platforms, IoT and enterprise data. Hover a card to explore.
Enterprise RAG HR AssistantRAGEnterprise RAG HR AssistantRetrieval-Augmented Generation assistant on Azure AI Foundry and Azure OpenAI that answers employee and leadership questions over internal HR data, with Pinecone vector search and role-aware prompt guardrails.RAGAzure AI FoundryAzure OpenAIPinecone
CMS Authoring MCP ServerMCPCMS Authoring MCP ServerWrite-capable MCP server for Contentstack / Contentful that gives an LLM agent governed access to design content models and generate, publish, and roll back content at scale.MCPAgentic AutomationLLM Tool UseJSON Schema
Modjoul IoT PlatformIoTModjoul IoT PlatformLed the frontend team on Modjoul's IoT asset-management dashboard, with secure AWS API Gateway and Cognito integrations.IoTAWSAPI GatewayCognitoEnterprise RAG HR AssistantRAGEnterprise RAG HR AssistantRetrieval-Augmented Generation assistant on Azure AI Foundry and Azure OpenAI that answers employee and leadership questions over internal HR data, with Pinecone vector search and role-aware prompt guardrails.RAGAzure AI FoundryAzure OpenAIPineconeCMS Authoring MCP ServerMCPCMS Authoring MCP ServerWrite-capable MCP server for Contentstack / Contentful that gives an LLM agent governed access to design content models and generate, publish, and roll back content at scale.MCPAgentic AutomationLLM Tool UseJSON SchemaModjoul IoT PlatformIoTModjoul IoT PlatformLed the frontend team on Modjoul's IoT asset-management dashboard, with secure AWS API Gateway and Cognito integrations.IoTAWSAPI GatewayCognito
Figma-to-Code MCP ServerMCPFigma-to-Code MCP ServerModel Context Protocol server that lets an LLM agent turn Figma designs into production-ready Next.js components already bound to Contentstack / Contentful data.MCPAI AgentsTool CallingFigma API
AI-Powered Interview & Candidate Screening PlatformAzure AI FoundryAI-Powered Interview & Candidate Screening PlatformInternal AI interviewing and screening application on Azure AI Foundry that evaluates candidate interviews and CVs and produces an explainable shortlist for the hiring team.Azure AI FoundryAzure OpenAIDocument IntelligenceAzure AI Language
Online Hiring PlatformAIOnline Hiring PlatformBuilt an emotion-based CV screening tool using facial recognition to help recruiters shortlist candidates faster.AIFacial RecognitionFull StackFigma-to-Code MCP ServerMCPFigma-to-Code MCP ServerModel Context Protocol server that lets an LLM agent turn Figma designs into production-ready Next.js components already bound to Contentstack / Contentful data.MCPAI AgentsTool CallingFigma APIAI-Powered Interview & Candidate Screening PlatformAzure AI FoundryAI-Powered Interview & Candidate Screening PlatformInternal AI interviewing and screening application on Azure AI Foundry that evaluates candidate interviews and CVs and produces an explainable shortlist for the hiring team.Azure AI FoundryAzure OpenAIDocument IntelligenceAzure AI LanguageOnline Hiring PlatformAIOnline Hiring PlatformBuilt an emotion-based CV screening tool using facial recognition to help recruiters shortlist candidates faster.AIFacial RecognitionFull StackCareer
Where I've built and led
5 roles across 4 companies, from hands-on full stack engineering to leading engineering teams and client delivery.
Oct 2025 – Present
Associate Technical Lead · Engineering Lead
Eight25Media
Engineering Lead / Engineering Manager for a B2B marketing platform, a multi-environment Next.js 15, Contentful and Vercel deployment. Directed a team of engineers through architecture, implementation and production; architected a dual-layer caching system (Next.js "use cache" plus Vercel CDN policies) that resolved a 62.9% cache-miss rate; engineered a multi-tier Contentful–Smartling localization pipeline; drove post-migration technical SEO (JSON-LD, metadata, sitemap, hreflang); and established a dual-remote Git workflow and CI/CD pipeline across the Eight25Media and GitHub organizations while owning client-facing technical delivery.
- Directed a team of engineers end to end, from architecture to production, for B2B marketing platform
- Architected a dual-layer caching system (Next.js "use cache" + Vercel CDN policies) that resolved a 62.9% cache-miss rate
- Engineered a multi-tier Contentful–Smartling localization pipeline for global B2B audiences
- Drove post-migration technical SEO: JSON-LD, metadata, sitemap and hreflang validation
- Set up a dual-remote Git workflow and CI/CD across two GitHub organizations and onboarded engineers
Next.js 15ReactTypeScriptContentfulVercelNode.jsGTMSegmentSmartlingCI/CD
Intermission
Scroll fatigue is real.
Fun fact: studies estimate the average smartphone user thumbs through about 90 metres of content a day, roughly the height of the Statue of Liberty. Your thumb is doing a triathlon and nobody clapped.
Scrolled on this page
0.0m
0% of a Statue of Liberty (93 m). Keep going, or take a break below.
So here is a 20-second break. Squash a few bugs, beat your best, then keep scrolling. The rest of my work is right below.
Score
0
Streak
–
Time
20s
Best
–
I'm looking to partner with teams that want to build agentic AI workflows and LLM-powered apps — from RAG assistants over their own data to MCP servers that let AI agents do real work
JavaScript
TypeScript
Python
.NET
Next.js
React
Node.js
NestJS
GraphQL
REST APIs
Contentful
Contentstack
Headless CMS
Vercel
AWS
Azure AI Foundry
Azure OpenAI
RAG
Pinecone
Vector Search
MCP Servers
AI Agents
Prompt Engineering
LLM Evaluation
Snowflake
MySQL
MongoDB
Firebase
CI/CD
TeamCity
Octopus Deploy
Technical SEO
Web Performance
Caching Architecture
Site Localization
Figma API
Agile Delivery
Engineering Leadership
Agentic Workflows
Tool Calling
LLM Orchestration
Azure AI Agent Service
Prompt Flow
AI Guardrails
LLM-as-a-Judge
Structured Output
Human-in-the-Loop
Design-to-Code Automation
Featured work
Case studies, in depth
Move your cursor over a project to look around it. Each one is a real system that shipped to real users.
enterprise-rag-hr-assistant.app
01 / 07Featured project
Enterprise RAG HR Assistant
Designed and built an enterprise Retrieval-Augmented Generation (RAG) assistant that answers employee and leadership questions over the company's internal HR knowledge base, including policies, handbooks, org data, and employee records, in natural language.
Vector layer: ingested, cleaned, and chunked internal documents, generated embeddings, and indexed them in a Pinecone vector database with metadata filtering; implemented top-K semantic search with relevance scoring and re-ranking to retrieve the highest-signal context per query.
Generation layer: orchestrated retrieval and generation through Azure AI Foundry, using Azure OpenAI Service GPT chat-completion and text-embedding deployments, Prompt Flow for orchestration, and Foundry evaluation and observability for answer quality, producing grounded, citation-backed responses.
Security & governance: engineered a layered prompt architecture with a base system prompt plus a dedicated security prompt that enforces role-based access control at inference time, so executives receive full organizational data while interns and junior roles are limited to permitted, non-sensitive records.
Responsible AI: grounding and hallucination mitigation with explicit "not found" fallbacks, Azure AI Content Safety filtering, prompt-injection defenses, and PII-aware handling of employee data.
RAGAzure AI FoundryAzure OpenAIPineconeEmbeddingsPrompt FlowRBACResponsible AI
figma-to-code-mcp-server.app
02 / 07Featured project
Figma-to-Code MCP Server
Built a Model Context Protocol (MCP) server that exposes Figma, Contentstack / Contentful, and a Next.js codebase as callable tools to an LLM agent, turning design handoff into an automated, agent-driven pipeline.
Design ingestion: the agent reads Figma design context (frames, layers, auto-layout, design tokens, typography and spacing variables) and translates it into production-ready React / Next.js components in TypeScript that match the existing component library and design-system conventions.
Data binding: automatically maps each generated component to the corresponding headless CMS content model and wires up live content via GraphQL / Content Delivery API, so generated UI ships bound to real CMS data rather than static markup.
Agent engineering: tool/function calling, schema-constrained structured output, deterministic code templates, and validation passes so agent output compiles and conforms to lint, accessibility, and type-safety standards, with human-in-the-loop review before merge.
MCPAI AgentsTool CallingFigma APINext.jsTypeScriptContentfulContentstackDesign-to-Code
cms-authoring-mcp-server.app
03 / 07Featured project
CMS Authoring MCP Server
Built a write-capable Model Context Protocol (MCP) server for Contentstack / Contentful that gives an LLM agent authenticated, governed write access to the CMS, automating work previously done manually by content engineers.
Content modelling: the agent designs and provisions content models and content types from natural-language or design-derived requirements, including fields, data types, validations, references, localization settings and relationships, using schema generation and the CMS Management API.
Content automation: generates and publishes entries in bulk, populating new models with structured content and handling references, assets and locale variants, with idempotent writes, dry-run previews, and rollback safety so repeated agent runs never duplicate or corrupt production content.
Governance: human-in-the-loop approval gates, scoped API credentials, and sandbox vs. production environment separation keep autonomous writes auditable and reversible.
MCPAgentic AutomationLLM Tool UseJSON SchemaContentfulContentstackCMS Management APIHuman-in-the-Loop
ai-powered-interview-&-candidate-screening-platform.app
04 / 07Featured project
AI-Powered Interview & Candidate Screening Platform
Built an internal AI interviewing and screening application on Azure AI Foundry that conducts and evaluates candidate interviews and automatically shortlists qualified candidates for the hiring team.
CV intelligence: parses and structures candidate CVs with Azure AI Document Intelligence, then semantically matches skills and experience against role requirements using embeddings and vector similarity.
Answer & behaviour analysis: uses Azure OpenAI Service models as an LLM-as-a-judge scorer against a structured competency rubric, with Azure AI Language for sentiment, key-phrase and tone signals, to assess both the substance of answers and behavioural indicators.
Decisioning: combines CV fit, answer quality, and behavioural scores into a weighted, explainable ranking with a per-candidate rationale for recruiters, reducing manual screening effort and standardising evaluation.
Responsible AI: rubric-based consistency checks, bias-mitigation prompt design, Azure AI Content Safety, and mandatory human review before any hiring decision, keeping the system decision-support rather than decision-making.
Azure AI FoundryAzure OpenAIDocument IntelligenceAzure AI LanguageLLM-as-a-JudgeEmbeddingsExplainable AIResponsible AI
paycor-report-migration-to-snowflake.app
05 / 07Featured project
Paycor Report Migration to Snowflake
Led a cross-functional team of engineers through the end-to-end migration of Paycor's reporting and client data from on-premises infrastructure to Snowflake, owning the project from discovery and architecture planning to final cutover.
Delivered the migration with Snowflake stored procedures and Python automation, coordinated data mapping and schema design, and established validation and testing protocols to catch discrepancies before go-live. The project secured nearly $1M in additional revenue and improved data accessibility, query performance, and scalability for Paycor's reporting and analytics.
SnowflakePythonSQLStored ProceduresData Migration
modjoul-iot-platform.app
06 / 07Featured project
Modjoul IoT Platform
Led the frontend team on Modjoul's IoT asset-management dashboard, translating device telemetry into actionable views for operations teams.
Managed AWS cloud deployments with secure API Gateway and Cognito integrations, and guided a sub-team through the full SDLC.
IoTAWSAPI GatewayCognitoReact
online-hiring-platform.app
07 / 07Featured project
Online Hiring Platform
Built an online hiring platform that screens candidates using emotion-based analysis and facial recognition, giving recruiters a faster way to shortlist applicants.
Handled both backend logic and frontend UI integration, including cloud deployments.
AIFacial RecognitionFull Stack