Wayfair logoWayfair Externship via Extern
Devarsh Prajapati portrait

Computer science senior building practical software skills

Fourth-year CS student with hands-on experience, focused on turning coursework and early projects into professional work.

View my workMessage Me

Work samples

Practical projects from coursework and early work experience that show technical skills, problem solving, and readiness for professional software roles.

  • Wayfair n8n AI Agent Engineering Externship
    Wayfair n8n AI Agent Engineering Externship
    Wayfair logo

    Wayfair · ✅ Verified by Extern · ⏱️ In progress

    Wayfair n8n AI Agent Engineering Externship

    Learn one of the most in-demand skills shaping the future of work: building AI agents. In this externship, you’ll step into the role of an AI Agent Developer and use n8n to design agents that think, plan, and act on real data — automating insights, decisions, and workflows. No coding experience required. By the end, you’ll create a live dashboard powered by your own AI agents, gaining hands-on experience that applies to any role or industry — from marketing and consulting to product management and data science.

    AI Workflow DesignAI Agent DevelopmentPresentation SkillsWeb Scraping & Data Extraction
  • ContextCode Live Demo
    ContextCode Live Demo

    Built an AI codebase assistant that indexes Python/JS/TS repos with Tree-sitter, chunking by function, class, and module so retrieval never splits a function mid-body; grounded answers in retrieved code with exact file:line citations; scaled indexing with Celery workers behind an async FastAPI, streaming progress over SSE; deployed a public demo hardened with Cloudflare Turnstile, Redis quotas, and per-IP rate limits, backed by 274 automated tests.

    FastAPICeleryTree-sitterChromaDBNext.jsMiniLMOpenAI embeddingsRailwayVercelCloudflare TurnstileRedispytestVitestPlaywright

About me

Fourth-year CS student with hands-on experience, focused on turning coursework and early projects into professional work.

I am Devarsh Prajapati, a senior Computer Science student (BSc Hons) at York University and an AI/ML intern. I build practical AI systems: codebase search and assistant tools, AI-powered Shopify visibility features, and agentized workflows from a Wayfair n8n externship. I work with Python, TypeScript, vector search, LangChain/LangGraph, LLaMA-family models, cloud deployments, and async systems. I am focused on making reliable, production-ready ML applications.

Externships

Wayfair n8n AI Agent Engineering Externship

In progress

Experience

AI/ML Intern

Automators Lab · May 2025 – Sep 2025

Education

York University

BSc. Honours in Computer Science · Class of 2026

Skills

PythonTypeScriptJavaScriptSQLJavaRLangGraphLangChainRAGModel Context Protocolembeddingsvector searchstructured outputsprompt engineeringOpenAIAnthropicGeminiPerplexityLLaMA/OllamaFastAPINext.jsReactNode.jsCeleryarqFlaskStreamlitPostgreSQLQdrantChromaDBRedisDockerRailwayVercelNorthflankGoogle CloudSystem DesignMulti-Agent SystemsREST API DesignDistributed SystemsCI/CD
Back to work
Wayfair ↗

✅ Verified by Extern · ⏱️ In progress

Wayfair n8n AI Agent Engineering Externship

Learn one of the most in-demand skills shaping the future of work: building AI agents. In this externship, you’ll step into the role of an AI Agent Developer and use n8n to design agents that think, plan, and act on real data — automating insights, decisions, and workflows. No coding experience required. By the end, you’ll create a live dashboard powered by your own AI agents, gaining hands-on experience that applies to any role or industry — from marketing and consulting to product management and data science.

AI Workflow DesignAI Agent DevelopmentPresentation SkillsWeb Scraping & Data Extraction

Overview

The externship trained participants to build AI agents using the n8n automation platform. The work involved configuring agents that plan and act on data, integrating flows in n8n, and assembling a live dashboard driven by those agents. Deliverables included a deployed n8n instance and a functioning automation flow.

Wayfair n8n AI Agent Engineering Externship

What I've accomplished

I built an n8n-based moodboard generator, authoring a Prompt Node that converted loose style inputs into precise 3x3 moodboard prompts and iterating system instructions for consistent tile counts and color naming.

Project breakdown

During the n8n setup, I created a Prompt Node that translated rough style inputs into precise 3x3 moodboard prompts. I iterated system instructions to enforce exact tile counts and cleaner color naming. The submission included multiple example prompts and a short reflection.

Google Docs
Access
View all work
Back to work

ContextCode Live Demo

Built an AI codebase assistant that indexes Python/JS/TS repos with Tree-sitter, chunking by function, class, and module so retrieval never splits a function mid-body; grounded answers in retrieved code with exact file:line citations; scaled indexing with Celery workers behind an async FastAPI, streaming progress over SSE; deployed a public demo hardened with Cloudflare Turnstile, Redis quotas, and per-IP rate limits, backed by 274 automated tests.

FastAPICeleryTree-sitterChromaDBNext.jsMiniLMOpenAI embeddingsRailwayVercelCloudflare TurnstileRedispytestVitestPlaywright
View all work
Back to work

SixRise Site

Built an AI visibility platform for Shopify stores that measures product recommendations by AI shopping engines, enforced a hallucination-safe publishing path using gpt-5-nano with structured outputs and deterministic verification, architected a two-service Shopify app isolating merchant credentials, and optimized the async job model to reduce idle infrastructure cost.

FastAPITypeScriptPostgresRedisShopifyPythonarqNorthflankNeonUpstashPerplexity Sonar
View all work