Full Stack Developer | AI Developer | Backend Systems
Full Stack Developer with 5+ years of on-and-off experience building independent projects — scalable web, mobile, and AI-integrated systems. Specialized in LLM integration, real-time WebSocket systems, Dockerized cloud deployments, and CI/CD automation.
01 / Projects
My family's competitive Wordle trash talk needed a multiplayer version — none existed, so I built one.
A real-time multiplayer word game with a Shannon entropy–based AI bot engine that maximizes information gain per guess. Features a constraint-satisfaction solver for edge cases, 5-tier ELO matchmaking (600–2000) with probabilistic human imperfection modeling, adaptive difficulty scaling, and 60+ AI-generated avatars via custom ComfyUI pipelines.
AI-powered website redesigner that crawls any site, analyzes brand identity with Claude, generates a premium redesign, and deploys it to a live URL — all in real time via Server-Sent Events streaming.
A web extension that scrapes job listings, parses structured data, and matches roles using resume-aware LLM analysis. Generates personalized cold emails with tone control via OpenAI API. Full automation pipeline: scrape → parse → match → generate → review.
An end-to-end n8n automation pipeline that monitors Gmail for job alerts (Indeed, Upwork, JobStreet), scores listings against my resume using GPT-4o with a hybrid AI + code salary algorithm, logs everything to Google Sheets, and sends Telegram notifications for high-scoring matches.
A hobby experiment — I wanted to explore Web3 by tinkering with open-source blockchain code and see how far I could push it.
A decentralized, fully secure blockchain platform built with Privy for seamless wallet authentication. Features trustless architecture, on-chain transactions, and a robust security-first approach to Web3 gaming.
A full-featured e-commerce platform for a bike shop, enhanced with AI-powered product recommendations and intelligent search. Built as a thesis project demonstrating LLM integration in online retail.
Have a product idea? I can help you ship it.
Start a Project02 / AI Showcase
Generating 60+ consistent avatars for WordWarz.io meant solving a core problem: AI models are unpredictable, and every word in a prompt matters. Here's the process — from prompt engineering to a fully automated pipeline.
Wording is everything in AI image generation — a single token can change the entire output. These comparisons show how prompt structure directly controls what the model produces.
How natural language vs structured tags changes what the model generates — "cat girl" becomes a literal cat.
same seed: 300003
Vague descriptions produce generic output — detailed tags create unique characters.
same seed: 510001
Words with multiple meanings confuse the model — "bat girl" could be a bat or a girl with bat wings.
same seed: 310001
Figurative speech gets interpreted literally — "fire in her eyes" produces actual flames.
same seed: 410001
KSampler Settings
30 steps with res_multistep sampler + ModelSamplingAuraFlow (shift 4.0) for clean Lumina-based generation; low cfg preserves natural detail.
With the right prompts figured out, I built a visual pipeline in ComfyUI — a node graph with full control over each generation parameter.
Then automated the whole thing — a Python script feeds modifier combinations into ComfyUI via API, generating unique avatars from a single prompt template.
Scripts handle auto-naming, BG removal, image optimization, and video compression — all automated in the pipeline.
Included in the scripts:
Files saved as category_variant-name.png
BiRefNet auto-strips backgrounds in pipeline
PNG → WebP, 90% smaller
ffmpeg H.264, 54MB → 1.4MB
MODIFIERS = {
"Hair & Expression": [
{"name": "Red Hair Peace",
"prompt": "red hair, peace sign"},
{"name": "Pink Hair Wink",
"prompt": "pink hair, winking, playful"},
{"name": "Blonde Smug",
"prompt": "blonde hair, smug expression"},
],
"Props & Accessories": [
{"name": "Boba Tea",
"prompt": "brown hair, sipping boba tea"},
{"name": "Catgirl Lollipop",
"prompt": "orange hair, cat ears, lollipop"},
],
"Gamer Variants": [
{"name": "Headphones Jacket",
"prompt": "headphones, gaming jacket"},
{"name": "Catear Streamer",
"prompt": "cat ear headphones, streamer setup"},
],
"Street Style": [
{"name": "Cap Chains",
"prompt": "cap, bubblegum, chain necklace"},
{"name": "Sunglasses Street",
"prompt": "sunglasses, bubblegum, street fashion"},
],
"Royalty": [
{"name": "Royal Crown",
"prompt": "crown, royal cape, proud expression"},
{"name": "Tiara Pearls",
"prompt": "small tiara, smug, pearl earrings"},
],
"Scientists & Tech": [
{"name": "Lab Coat Goggles",
"prompt": "lab coat, safety goggles"},
{"name": "VR Scientist",
"prompt": "VR visor, tech gear, futuristic"},
],
}Modifier combos, prompt templates, batch queue
Node pipeline processes each prompt automatically
24 unique avatars, production-ready
And here's what the system produces — 60+ avatars, all from one pipeline.
1girl/1boy, chibi, bust portrait, sharp eye highlights, vibrant anime color palette, cel-shading, crisp lineart, white background, centered composition, high detail face
Hover or tap avatars to see the modifier prompt used for each variation
Style is extracted via CLIP Vision and injected through IPAdapter Advanced, while text prompts control pose and expression independently.
DreamShaper XL Lightning
Base model
IPAdapter SDXL ViT-H
Style transfer
CLIP-ViT-H-14
Vision encoder
Style Transfer Precise
Weight type
Given a single character illustration, generate consistent poses and expressions using IPAdapter style transfer — preserving the original art style across every angle.
Front
Back
Shocked
Side
Using ControlNet Depth to preserve a mannequin's pose and body structure, then generating photorealistic clothing variations and tattoo removal from text prompts.
RealVisXL V5.0 Lightning
Base model
ControlNet Depth SDXL
Pose preservation
Depth Anything V2
Depth preprocessor
DPM++ SDE Karras
Sampler
A blank mannequin serves as the base pose. ControlNet extracts the depth map to lock the silhouette, while the model generates different outfits from text prompts with dynamic ControlNet strength per clothing type.
Leather Jacket
Overcoat
Trench Coat
Dress Shirt
Interested in working together?
Contact Me03 / Skills
Scalable full-stack applications, REST APIs, authentication, SQL & NoSQL databases, analytics dashboards, and data-driven architecture.
React Native, Swift, and Kotlin apps from concept to store deployment, with push notifications and native integrations.
LLM integration, prompt engineering, image and video generation, and AI-powered product workflows.
Docker, CI/CD pipelines, Google Cloud, VPS administration, and automated deployment strategies.
04 / Journey
Self-directed, on-and-off development across frontend, backend, and database layers. Built and deployed independent projects including REST APIs, real-time systems, and AI-integrated applications. Managed Docker containers, Linux VPS infrastructure, and CI/CD deployment workflows.
Completed a comprehensive IT program covering software development, database management, networking, and system analysis with hands-on capstone project experience.
05 / About
I'm a Full Stack Developer with 5+ years of on-and-off experience building independent projects — scalable web, mobile, and AI-integrated systems. Specialized in LLM integration, real-time WebSocket systems, Dockerized cloud deployments, and CI/CD automation.
My toolkit spans the entire stack — JavaScript, TypeScript, Python, React, React Native, Next.js, Node.js, Express, and PostgreSQL. I bring hands-on experience in AI workflow automation, including LLM integration with Claude and GPT, Stable Diffusion, ComfyUI, and prompt engineering.
Proven ownership of end-to-end system architecture, backend performance optimization, and production infrastructure. Whether it's a real-time multiplayer game, an AI-powered redesigner, or a blockchain DApp, I ship products with meticulous attention to detail.
06 / Contact
Open to collaborations, freelance work, and exciting opportunities.