This Portfolio (v2)
A Laravel 13 app with a typed admin panel, RAG-powered AI chat grounded in posts/projects, Tailwind v4 dark design system, OG image generator, and full SEO surface — so the site evolves without a rewrite.
Al Amin Ahamed — senior software engineer, 5 years of it on the web. I build things that have to keep running after the invoice clears, and I write down what breaks.
Selected work
A Laravel 13 app with a typed admin panel, RAG-powered AI chat grounded in posts/projects, Tailwind v4 dark design system, OG image generator, and full SEO surface — so the site evolves without a rewrite.
Tundra ships a single Rust binary that replaces the panel — declarative site config, native PHP-FPM and Node pool management, Caddy + automatic TLS, and a typed REST/CLI surface. Operators get reproducible builds, one-command deploys, and a real diff before any production change. No license fee, no agent footprint, no language runtime to maintain.
One WP-CLI command seeds 500 products, orders, customers, reviews, coupons across 14 generators with locale-aware data. 131 Playwright E2E tests pin every generator and cleanup mode wipes test data before launch.
"At work: Senior Software Engineer at Codexpert. Deep focus on EasyCommerce — AI-driven product management, multi-vendor marketplace features, and performance work. Shipped several extensions to the WordPress.org repo thi..."
More →Writing
I completed six Anthropic Academy courses covering the Claude API, Model Context Protocol, subagents, agentic workflows, Claude Code, and AI fluency — each with a verified certificate from Anthropic Education.
How EasyCommerce manages LLM prompts across Claude, OpenAI, and DeepSeek with a versioned registry, structured evals in CI, and a rollback path that does not require a deployment.
How to build a complete RAG pipeline in Python without LangChain or LlamaIndex — chunking, embedding with text-embedding-3-large, pgvector retrieval, and grounded generation with Claude — with the tradeoffs that matter at production scale.
How codebase-research-agent exposes a tool-using AI agent as a Claude Code MCP server — JSON-RPC over Streamable HTTP, tool registration, streaming SSE, and the four things that broke in production before it worked reliably.
Stack snapshot