Skip to content

kudzai prichard

Backend Software Engineer · Distributed Systems · AI Integration

Building distributed backend systems and cloud-native APIs at scale. Specializing in AI/ML integration, model deployment, and AWS infrastructure. Shipping production systems that process high volumes of data reliably.

About

Engineer who builds distributed backend systems and ships them. ML pipelines processing high volumes of data, models deployed with high accuracy in production, full-stack apps serving a multitude of users. Fluent in Python, C#, TypeScript, and making machines do useful things. Always: building the next thing.

Tech Stack

  • AI/ML: TensorFlow, Keras, PyTorch, scikit-learn, OpenCV, NLP, OCR, Google Gemini
  • Backend: Python, C#, .NET, Java, Spring Boot, FastAPI, Flask
  • Frontend: Next.js, React, TypeScript, Angular, TanStack Query, Tailwind CSS
  • Cloud & DevOps: AWS, Azure, Docker, Vercel, CI/CD, Git

Specializations

  • Distributed Systems & Backend Architecture
  • AI/ML Integration & Model Deployment
  • Cloud-Native APIs (AWS / Azure)
  • Microservices & Event-Driven Systems
  • Voice AI & Automation
  • Full Stack Web Development

Projects

AURA (WIP)

Distributed phishing-detection platform with a closed model feedback loop. A FastAPI backend handles inference, model versioning, and online retraining; a Chrome extension delivers real-time verdicts inside Gmail; a Next.js analyst dashboard manages the review and redeployment cycle — all connected through a PostgreSQL-backed audit trail.

Technologies: Python, FastAPI, scikit-learn, PostgreSQL, Next.js, TypeScript, Docker

GitHub

SENTRY (WIP)

Two-stage distributed email analysis pipeline. A FastAPI service integrates Groq for low-latency inference and Google Gemini for deep page analysis — decoupled via async background tasks so the fast path is never blocked. Deployed with async SQLAlchemy and rate-limited token auth for extension clients.

Technologies: Python, FastAPI, Groq, Google Gemini, Playwright, Next.js, TypeScript

GitHub

METIS (WIP)

Clinical AI backend deploying a Neural Thompson Sampling model (PyTorch) as a REST API for real-time treatment recommendations. Model inference, clinician feedback ingestion, and posterior updates are handled by a FastAPI service backed by PostgreSQL and Neo4j — with deterministic safety gates enforced at the API layer before any model output is returned.

Technologies: Python, PyTorch, FastAPI, PostgreSQL, Neo4j, Next.js, React

GitHub

Coin Compass (LIVE)

Eight-service microservices architecture for cryptocurrency price prediction. Spring Boot handles API gateway, JWT/RBAC auth, centralised config, live Binance data ingestion, and user services; a Python ML service exposes a trained model via REST. Fully containerised with Docker and designed for independent service deployment.

Technologies: Java, Spring Boot, Python, Flask, scikit-learn, MySQL, MongoDB, Docker

GitHub

UBot MT4 (LIVE)

Automated trading system (Expert Advisor) built in MQL4 for MetaTrader 4. Analyses historical market data to identify patterns and executes long and short trades autonomously — with configurable stop loss, take profit, position scaling, and trailing profit management. Includes a real-time dashboard and compiles to a deployable .ex4 binary.

Technologies: MQL4, MetaTrader 4, Algorithmic Trading, Expert Advisor

GitHub

Spring Real Estate API (LIVE)

Production REST API deployed on AWS and Vercel connecting property agents with buyers. Spring Boot backend with JWT-secured endpoints, role-based access control, relational schema design, and a CI/CD pipeline — built from scratch and taken to live production.

Technologies: Java, Spring Boot, MySQL, JWT, AWS, Vercel, CI/CD

GitHub

View all projects on GitHub

Experience

Software Engineer @ Sybrin Imaging Solutions

Aug 2024 - Jul 2025

Industrial attachment at an enterprise fintech company serving tier-1 African banks and insurers — Ecocash, CABS, Stanbic Bank, BancABC, and Old Mutual — across 6+ markets. Owned the full delivery loop: distributed system design, cloud deployment on AWS and Azure, ML model integration, and live client delivery.

  • Architected and deployed a high-volume document processing platform (C#, .NET, Azure, OpenAI) to production — handling large-scale OCR workloads for Ecocash, CABS, and Stanbic Bank across a distributed cloud pipeline
  • Designed and built the CABS Internet Banking API from scratch on AWS — RESTful endpoints, background Watcher/Indexer service, Audit Logs, and MFA for full regulatory compliance across UAT, QA, and Production environments
  • Integrated and deployed custom ML models (Python, TensorFlow, OpenCV) into a production document pipeline for BancABC — extracting structured data from high-volume scanned banking documents with high accuracy
  • Shipped 2 production AI integration pipelines for BancABC: an RTGS instruction processor combining OCR and ML inference, and an HR automation pipeline with NLP-based resume parsing, candidate scoring, and automated scheduling
  • Delivered across Old Mutual's large-scale distributed microservices platform (AWS, Docker) spanning 6 African countries — contributed to system design reviews, BRD sessions, and client training
  • Architected a reusable UI configuration layer for Sybrin's cloud platform — adopted as the standard integration pattern across multiple tier-1 banking clients

Technologies: C#, .NET, Python, TensorFlow, OpenCV, AWS, Azure, Docker, Next.js, MySQL

Co-Founder & Engineer @ Teleagents

2025 - Present

Building an AI voice-infrastructure platform that deploys human-sounding voice agents for inbound support, outbound sales, and 24/7 call-centre automation. Currently in closed beta with enterprise clients across Zimbabwe.

  • Architected the full voice agent pipeline (Next.js, Python, FastAPI) handling both inbound and outbound call flows autonomously
  • Closed beta with enterprise clients across Zimbabwe
  • Designed the product, infrastructure, and go-to-market strategy from the ground up as co-founder

Technologies: Python, FastAPI, Next.js, TypeScript

Co-Founder & Engineer @ OurAfrica

2025 - Present

Building an offline-first cross-platform e-learning solution for low-bandwidth users across Africa — available on web, desktop, and Android with download-and-study, progress sync, and verifiable certificates.

  • Shipped web, desktop (Tauri), and Android (Expo) clients targeting low-bandwidth African markets
  • Designed offline-first sync architecture so learners can study without an active internet connection
  • Built Spring Boot backend hosted on AWS EC2 with full CI/CD pipeline

Technologies: Spring Boot, Next.js, Tauri, Expo, AWS EC2

Software Engineer @ Replica Systems

Jan 2022 - Jun 2022

Industrial attachment delivering a full-stack site-management platform for a construction client and taking ownership of production websites including the Replica Systems corporate site.

  • Built a full-stack site-management platform (Spring Boot, PostgreSQL, JWT, Angular) from blank repo to live production on AWS and Vercel via CI/CD
  • Took ownership of the Replica Systems corporate site (React, Next.js) — covering UI development, domain registration, cloud hosting, and SEO optimisation

Technologies: Spring Boot, PostgreSQL, JWT, Angular, React, Next.js, AWS, CI/CD

Contact

Get in touch via email at [email protected], GitHub at @kudzaiprichard, LinkedIn, or Twitter at @kudzaiprichard.

Or use the contact form to send a message.

Interactive Terminal

A fully interactive shell session. Type a command and press Enter to run it, or simply ask a question in plain English and the built-in AI assistant (Kudzai's terminal agent) will answer and can navigate the site for you. Available commands include: ask, help, whoami, neofetch, htop, history, date, echo, man, ls, cd, cat, pwd, ping, ssh, curl, sudo, git log, git blame, vim, ascii, hack, matrix, snake, adventure, clear, exit. Press Tab to autocomplete. Use the Up and Down arrow keys to recall previous commands.

visitor@kudzai:~$