Hi, I'm Freddie
A Builder and Founder passionate about creating products that solve real business problems.
FA

About

I enjoy taking ideas from concept to production, creating software that is scalable, reliable, and built with users in mind. I've worked with startups and businesses to develop SaaS platforms, internal business systems, automation workflows, and customer-facing applications. One of my most impactful projects was engineering a Food Ordering System for Didi Jollof in collaboration with a German startup. The platform processed over 3,000 orders and contributed to more than GH₵1.5 million in revenue within eight months across WhatsApp and web channels.

Work Experience

Skills

React
Tanstack Stack
Next.js
Typescript
Express.js
Node.js
Python
Postgres
MongoDB
Drizzle ORM
Prisma
Convex
Docker
Kubernetes
Cloudflare Workers
TailwindCSS
My Projects

Check out my latest work

I've worked on a variety of projects, from simple websites to complex web applications. Here are a few of my favorites.

Createit Africa Summit

Built a full-stack event management platform for CreateIT Africa, handling multi-tier registration for attendees, exhibitors, and vendors with live payments, automated email confirmations, and a full admin dashboard for managing speakers, sessions, sponsors, and SMS campaigns.

React 19
Typescript
TanStack Start
Cloudflare Native (R2, Workers, D1)
Drizzle ORM
Paystack
BetterAuth
Tailwind CSS
GSAP
Shadcn UI

Waftstore

This is an AI-powered multi-branched commerce platform built to help businesses launch, manage, and scale their online stores from a single ecosystem. It combines marketplace infrastructure with an intelligent AI Sales Agent that lives in the social media handle of your choice to help assists customers, recommends products, and automates sales conversations to improve conversions.

React 19
Tanstack Start
Typescript
Cloudflare Native (R2, Workers, D1)
Drizzle ORM
TailwindCSS
Paystack
Shadcn UI

Resona

Resona is an AI-powered voice platform I built for my church to streamline the production of voice-overs for advertisements, event promotions, announcements, and media campaigns. It features text-to-speech, voice cloning, multilingual narration, customizable voice personalities, emotion and pacing controls, and high-quality audio exports.

NextJS 16+
TypeScript
PostgreSQL
Drizzle ORM
TailwindCSS
Shadcn UI
Clerk
Cloudflare R2
Paddle

PolyraHR (SaaS)

PolyraHR is a modern, cloud-based Human Resource Management System designed to help organizations efficiently manage their workforce across multiple departments, branches, and locations. Inspired by the robustness of Frappe HR but rebuilt with a modern TypeScript-first stack.

Tanstack Start
Typescript
PostgreSQL
Drizzle ORM
TailwindCSS
Shadcn UI
BetterAuth
Paddle
Cloudflare Workers

Matteblac Website + Custom CMS

A bespoke portfolio platform and CMS engineered for a creative media brand, combining immersive content presentation with streamlined management of projects, media assets, and client inquiries through a unified administrative dashboard.

React 19
Tanstack Start
Typescript
PostgreSQL
NeonDB
Drizzle ORM
TailwindCSS
Shadcn UI
Cloudflare Native (R2, Workers)
Hackathons

I like building things

Some of my sharpest memories from university are from hackathons, three weekends where people dropped everything, showed up with laptops and ideas, and built something real together. It changed how I think about what's actually possible in a short amount of time.

GDSS 2026 Hackathon

GDSS 2026 Hackathon

In-person

Built an image-to-IMDB tool that auto-fills 10 product master attributes (barcode, brand, weight, category, etc.) from a single product photo. Used a vision-language model pipeline with OCR, regex validation, and duplicate-merge suggestions, outputting a structured CSV/Excel file ready for database upload.

2nd Place Winner
Website
GitHubGithub
VahanBima CLTV Prediction

VahanBima CLTV Prediction

Kaggle, Remote

Built a machine learning model to predict Customer Lifetime Value (CLTV) for a leading Indian motor insurance company, enabling tiered customer segmentation for personalized services. Used LightGBM/XGBoost with SHAP-based interpretability, evaluated on R² score.

Garbage Classification

Garbage Classification

Kaggle, Remote

Built a garbage classification web application using PyTorch and Streamlit. Fine-tuned a pretrained ResNet50 model to automatically sort waste into categories, reducing reliance on manual hand-picking and minimizing health risks for waste workers.

Contact

Get in Touch

Want to chat? Just shoot me a dm with a direct question on twitter and I'll respond whenever I can. I will ignore all soliciting.

GitHub
LinkedIn
X