EMMANUEL
Good day

I am Emmanuel Chimezie.
A Computer Engineer

Open to AI Engineering & App Development roles
AI Systems Engineer·Prompt Architect·Full-Stack Developer

I specialize in engineering structured prompt frameworks and building full-stack AI software applications. By combining computer engineering fundamentals with advanced generative workflows, I turn raw model capabilities into intuitive, user-ready applications.

Portrait of Chimezie Emmanuel Uzochukwu
Focus Area

About Me

Holding a B.Eng. in Computer Engineering from Oduduwa University, I specialize in prompt engineering, LLM logic design, and full-stack AI application development. My work centers on translating functional user needs into precise system prompts, agentic workflows, and production software applications.

From AI-moderated social debate software to multi-agent generative visual pipelines and multi-service aggregator apps, I use modern vibe coding, structured frameworks, and rapid prototyping tools to turn abstract ideas into fully operational digital products.

Location & Availability

Abuja, Nigeria (WAT / GMT+1) · Global Remote

Active & Available
Capabilities

Technical Expertise

Technical Skills Proficiency
Prompt Architecture App Development LLM Workflows System Architecture Generative Pipelines Full-Stack & APIs Prompt Architecture: 95% System Prompts, Logic Chains App Development: 90% React, TypeScript, Next.js LLM Workflows: 92% Claude API, Logic Guardrails System Architecture: 85% Computer Eng, UI/UX Logic Generative Media: 88% Image Gen APIs, Asset Pipelines Full-Stack & APIs: 82% Node.js, Supabase, Web APIs

APEX — SYSTEM PROMPT ARCHITECTURE & INTELLIGENCE

System Prompts · Agentic Workflows · Context Guardrails · Fallacy Logic

CORE — AI APPLICATION DEVELOPMENT & FULL-STACK

TypeScript · Node.js · Vibe Coding · Supabase · Modern Web Backends

FOUNDATION — COMPUTER ENGINEERING & SYSTEMS

Hardware Diagnostics · Technical Operations · Data Networks · Problem Solving

Prompt Architecture & LLMs
Advanced Prompt Engineering System Prompt Design Multi-Stage Reasoning Pipelines Fallacy Detection Logic Model Guardrails & Context Control
Software Application Building
TypeScript / JavaScript Node.js Full-Stack Prototyping Database & API Integration Supabase & Modern Backends
AI Workflows & Prototyping
Vibe Coding Workflows Claude Artifacts & Rapid Builders Grok & xAI Workflows Lovable Prototyping Generative Media Pipelines
System Design & Product
UI/UX Logic Structuring Workflow Automation Technical Problem Solving

Let's build something together

Open to AI Engineering, Prompt Architecture, and AI Application Development roles. Send a direct message below:

alexemmanuelz24@gmail.com
+234 8134328147
DOWNLOAD CV
LinkedIn
X (Twitter)

Featured AI Applications

Chain Stories — One Line at a Time

LIVE PROTOTYPE
  • Collaborative storytelling where each person adds exactly one line to a shared chain — “Sign the corner” with a unique lowercase username, then leave a line for the next writer to find. Paper-inspired UI with Timeline and Archives views.
  • Chains inactive for 30+ days move to Archives (or are deleted if under 5 lines). Built as a lightweight React app with a custom paper/ink design system, focused on the simple joy of passing a story forward one strip of paper at a time.
Frameworks: React Vite Custom CSS (paper theme) Local / shared storage
Key OutcomeA calm, paper-like collaborative writing experience — unique author handles, one-line-at-a-time chains, automatic archive lifecycle, and a clear path from “Sign the corner” onboarding into an active timeline of stories others can continue.
Application Proof
Chain Stories — Sign the corner onboarding Chain Stories — Timeline and empty state Chain Stories — Active chain / writing view
How It Was Built
Core Concept & Mechanics

A React web app for collaborative, one-line-at-a-time storytelling. Writers “Sign the corner” with a unique lowercase username (letters only, no spaces, numbers, or symbols), then leave a single line for someone else to find and continue. The experience is framed like strips of paper passed hand to hand — calm, intentional, and deliberately limited to one line per turn.

Identity & Access

Unique author handles are required and can be changed later. The live prototype focuses on lightweight identity and shared chain state rather than full account systems, keeping the barrier to writing as low as possible.

Tools & Stack

React + Vite, custom paper/ink CSS design system (warm paper backgrounds, seal-red accent, Fraunces / Source Serif 4 typography), and browser storage for local profiles and shared chains. Deployed on GitHub Pages.

Key Features (Live)
  1. Sign the corner — Onboarding to pick a unique lowercase author name before writing.
  2. One line at a time — Each contribution is a single line; the next writer continues the chain.
  3. Timeline — Active chains visible for others to find and extend.
  4. Archives — Chains inactive 30+ days move to Archives; under 5 lines may be deleted.
  5. Paper UI — Soft cream paper surfaces, folded-card feel, and a restrained seal-red accent.
  6. Guide & Board — Supporting views for orientation and shared activity.
Key Challenge Solved — Keeping Collaboration Simple and Human

Challenge: Most collaborative writing tools become complex dashboards or free-form editors that lose the intimacy of passing a story along.

Solution: Strict one-line turns, a paper metaphor, unique author handles, and an automatic archive lifecycle keep the product focused on the act of writing for the next person — not on managing accounts, permissions, or long-form drafts.

Scope Note

Current live build prioritizes the core loop (sign → write one line → discover on timeline → archive). Richer product directions (AI line scoring, cinematic Watch mode, invite-only Premium chains, full auth) remain on the roadmap and are described in earlier design notes; they are not all active on the public GitHub Pages deployment.

The Lazy App — Multi-Service Aggregator

PROTOTYPE
  • Cross-references apartments, travel, delivery, dispatch, and professional services in one dashboard — matched to the user's own taste and budget.
  • Every listing shows its real service provider; selecting one redirects out to that provider's page to complete the actual booking or transaction.
Frameworks: React / Node.js Supabase (PostgreSQL) Claude Artifacts Serverless / Edge
Key OutcomeSolves fragmented service access — one dashboard replaces visiting multiple separate apps and sites, with an API normalization layer and SWR caching keeping it fast and cheap to run.
Application Proof
Lazy App ingredient input screen Lazy App generated recipe output Lazy App service comparison view
How It Was Built
Tools & Stack

Built with a React / Node.js frontend, using Supabase (PostgreSQL + Auth) as the backend database, rapidly prototyped by generating and refining modular UI components via Claude Artifacts.

Integrations

Integrated third-party REST APIs into a unified middleware layer to aggregate, parse, and render service data within a single user dashboard. Spans multiple categories — apartments, travel, delivery, dispatch, and professional services — letting users cross-reference options against their own taste and budget in one place. Each result surfaces its actual service provider, and selecting one redirects the user to that provider's site to complete the booking or transaction.

Role: Solo Full-Stack Developer

Managed the entire scope from API integration design and data transformation to UI components and serverless deployment.

Technical Decisions
  1. Unified API Normalization Layer — Built a client-side adapter pattern that transforms inconsistent third-party JSON responses into a single internal schema before passing data to UI components.
  2. Stale-While-Revalidate (SWR) Caching — Utilized aggressive client caching strategies to minimize unnecessary third-party API calls, drastically improving load speed and avoiding API rate limits.
  3. Zero-Compute Serverless Architecture — Kept infrastructure overhead near zero by deploying frontend assets to edge locations and relying on serverless edge functions for API routing.
Key Challenge Solved — Fragmented Service Access

Challenge: Users had to visit multiple separate websites and apps individually just to find and use the tools or services they needed — apartments, travel, delivery, dispatch, professional services — creating friction and wasted time across a fragmented set of destinations.

Solution: Built a single aggregator app that houses the functionality of multiple third-party services in one unified dashboard, letting users cross-reference options across categories against their own taste and budget to surface the best alternative. Each listing indicates its actual service provider, and clicking through redirects the user to that provider's page to complete the booking — the app handles discovery and comparison, not the transaction itself.

Debate & Poetry Arena — Dual-LLM Debate Platform

LIVE APPLICATION
  • Watch or host live, upcoming, past, and local debates — register by setting the topic, time, and scoring preferences in a few steps.
  • Powered by a dual-LLM debate engine (Claude 3.5 Sonnet vs. GPT-4o) with real-time guardrails, plus live poetry challenges for spoken-word performers.
Frameworks: Claude 3.5 Sonnet GPT-4o Python (FastAPI) WebSockets React / Next.js
Key OutcomeCombines a dual-LLM debate engine with a live event platform — turning debate and poetry into accessible, schedulable, spectator-friendly content instead of one-off text exchanges.
Application Proof
Debate application arena overview AI fallacy analysis breakdown Debate topic list
How It Was Built
LLM Engine & APIs

Powered by Anthropic Claude 3.5 Sonnet (selected for complex reasoning and structured rhythmic phrasing in poetry) working alongside OpenAI GPT-4o (configured as a fast, opposing debate persona).

Agent Orchestration & Communication

Built using a custom Python agentic workflow using state graphs rather than heavy third-party agent frameworks. The system coordinates turn-taking, dynamic response injection, and context passing sequentially via event-driven state nodes.

Frontend / Backend Stack

React / Next.js frontend with Tailwind CSS for dynamic turn visualization; Python (FastAPI) backend utilizing WebSockets for low-latency streaming of agent outputs.

Role: Lead AI Architect & Full-Stack Developer

Formulated the multi-agent orchestration architecture, prompt management system, real-time guardrails, and dynamic UI state sync.

Technical Decisions
  1. Sliding Context Window with Summarization — Preserved agent performance and lowered token costs by maintaining a rolling memory window that dynamically summarizes past rebuttal turns into compact system context.
  2. Intermediary Guardrail Node — Added a lightweight validation pass between turns to verify output format, catch repetitive phrasing, and enforce word-count boundaries before rendering responses to the client.
Key Challenge Solved — Debate & Poetry Accessibility

Challenge: Debates — live, upcoming, past, or local — and spoken-word poetry were scattered and hard to discover, leaving audiences with little consistent way to find and engage with them, and limiting how entertaining and far-reaching debate and poetry could actually be.

Solution: Built a platform where users log in, register for a debate by setting the time, topic, and scoring preferences, and can then watch live, upcoming, former, or local debates in one place — turning debate into an accessible, spectator-friendly experience. Extended the same platform to poetry with live poetry challenges, letting poets post and perform live online alongside the debate content.

Key Design Decision — Keeping Agents On-Topic & Distinct

Designed structural system prompts featuring explicit persona rules and objective constraints (e.g., "Address point B made by Opponent, limit rebuttal to two stanzas, and do not repeat arguments from Turn 1"). This prevented agents from losing topic context or slipping into passive agreement loops.

NFT Forge — Generative AI Art Platform

LIVE APPLICATION
  • Powered by Stable Diffusion APIs with a custom Python pipeline (Pillow & OpenCV) for post-processing, trait compositing, and seed variation control.
  • Asynchronous worker queue (Celery & Redis) handles heavy model inference and batch rendering, with automated Web3 metadata generation before assets hit storage.
Frameworks: Stable Diffusion API Python (FastAPI) Celery / Redis Node.js / React Supabase
Key OutcomeFull-stack AI systems engineering end-to-end — from prompt frameworks and batch rendering scripts to the user interface and database sync — solving visual consistency across batches through deterministic seed locking and ControlNet conditioning.
Application Proof
NFTForge landing interface NFTForge prompt generator NFTForge generated output
How It Was Built
Image Generation & Processing

Powered by Stable Diffusion model APIs for base image generation, combined with a custom Python pipeline using Pillow and OpenCV for image post-processing, trait compositing, and seed variation control.

Language & Framework Stack

Python (FastAPI) for the image generation pipeline and batch rendering backend; Node.js / React with Supabase for user management, asset metadata handling, and database storage.

Role: Full-Stack AI Systems Engineer

Designed and implemented the system end-to-end, from prompt engineering frameworks and batch rendering scripts to the full-stack user interface and database sync.

Technical Decisions
  1. Asynchronous Worker Queue — Implemented background task workers (Celery & Redis) to handle heavy model inference and batch image rendering without blocking HTTP thread execution.
  2. Automated Metadata Extraction — Built a pipeline step that auto-generates compliant Web3 metadata JSON schemas directly from batch render outputs before pushing assets to storage.
Key Challenge Solved — Visual Consistency Across Batches

Challenge: Maintaining coherent art style, line weight, and feature alignment across high-volume batch generations.

Solution: Used deterministic seed locking coupled with ControlNet conditioning and dynamic negative prompt injection to lock key stylistic traits across randomized asset outputs.

Open to AI Engineering roles · Remote / Abuja
What I Do

I turn LLM capability into shipped AI products.

AI Systems Engineer and Prompt Architect with a Computer Engineering foundation — building structured prompt frameworks, LLM workflows, and full-stack AI applications that users can actually operate.

4+
AI Apps Shipped
3+
Years Building
95%
Prompt Focus
∞
Remote Ready
Location
Abuja, Nigeria
Experience
3+ Years
Specialization
AI & Prompt Eng.
Education
B.Eng Computer Engineering
Documents

Download My Resume

Get a detailed overview of my professional experience, skills, and achievements.

Engineer CV

ATS-optimized resume highlighting AI systems engineering, prompt architecture, LLM workflows, and application development experience. Formatted for clear parsing and keyword alignment in Applicant Tracking Systems.

ATS-Ready PDF Single-column
Download Engineer CV ↓
Summary

Professional Summary

Results-driven AI Prompt Engineer and Application Developer with experience designing multi-stage prompt logic, building full-stack AI web prototypes, and shipping generative workflows into usable products — from AI-moderated debate platforms to multi-character generative art pipelines.

Prompt Architecture & LLM Logic

System prompts, agentic workflows, context guardrails, and fallacy-aware reasoning pipelines that keep model behavior reliable in production UIs.

AI Application Development

End-to-end AI software with TypeScript, Node.js, Supabase, and modern builders — structured prompts turned into products users can operate.

Engineering Foundation

Computer Engineering background with systems diagnostics, technical operations, and problem-solving across hardware and software environments.

Experience

Professional Experience

Career path spanning AI application development, technical operations, and computer systems engineering.

Mar 2023 — Present
AI Prompt Engineer & Application Developer
Independent Specialist / Freelance
  • Built multi-stage prompt systems and agentic workflows for production-style AI apps
  • Shipped AI moderation, structured debate, and generative media platforms end-to-end
  • Combined TypeScript, LLM APIs, and Supabase into user-ready full-stack prototypes
Prompt Engineering TypeScript LLM APIs Supabase
Oct 2023 — Oct 2024
Technical Operations Support
Nigerian Bulk Electricity Trading Company
  • Resolved operational system issues and improved day-to-day workflow reliability
  • Supported infrastructure troubleshooting across technical process functions
Operations Troubleshooting Systems Support
Jun 2019 — Aug 2021
Computer Systems Engineer
Pearl Pearl, Ikeja, Lagos
  • Led hardware diagnostics, software configuration, and system maintenance
  • Delivered client and internal troubleshooting across mixed tech environments
Hardware Diagnostics System Config
Capabilities

Technical Skills

Core proficiency across prompt architecture, AI application building, and systems engineering.

Prompt Architecture95%
LLM Workflows92%
App Development90%
Generative Pipelines88%
System Architecture85%
Full-Stack & APIs82%
Claude Grok TypeScript React Node.js Supabase Prompt Logic Lovable Web APIs
Foundation

Education

2017 — Sept 2023
B.Eng. Computer Engineering — Second Class Upper
Oduduwa University, Ipetu Modu, Osun State
Key Recognitions

Awards & Certifications

Awards
  • Most Resourceful Student
Certifications
  • Generative AI
  • GEN.AI-for growth marketing
  • GEN.AI- The future of UIUX design
  • AI Prompt Engineering
  • Speaker for Computer Engineering
  • Mathematics Brain Challenge Winner
  • University degree certificate
  • NYSC

Let's build something

Open to AI Engineering, Prompt Architecture, and AI Application Development roles. Reach out and let's talk.

Engineer CV · ATS-ready PDF Download CV ↓