Hi, I'm Takudzwa Shumbamhini
Senior Software Engineer specialising in AI, computer vision, and IoT-integrated security platforms. I build production ML inference pipelines, real-time event-driven systems, and intelligent connected devices.
About Me
I am a Senior Software Engineer with 5+ years building production AI and computer vision systems, backend infrastructure, and IoT-integrated security platforms. At Cognitive Systems, I have led the development of real-time CCTV analytics — from training and deploying object detection models (YOLO, ConvNeXt, Faster R-CNN) to building multi-threaded inference pipelines, behaviour analytics engines, and automated alert dispatch systems.
My work spans the full stack of intelligent systems: ML model training and edge deployment, MQTT/RabbitMQ event-driven architectures, tamper-detection security for Linux-based IoT devices, and CI/CD infrastructure using Docker and Ansible. I specialise in taking models from selection through training to live deployment on edge devices in security-critical environments.
Skills & Expertise
AI & Computer Vision
Models & Frameworks
TensorFlow, Keras, YOLO, ConvNeXt, Faster R-CNN, YOLOX
Vision Libraries
OpenCV, dlib — object detection, image segmentation, correlation tracking
Production AI
Inference pipelines, edge deployment, behaviour analytics, real-time alerting
IoT & Embedded Systems
Devices
Raspberry Pi, Arduino, Sonoff Wi-Fi Smart Switches
Messaging & Protocols
MQTT (Mosquitto), AMQP (RabbitMQ), GPIO integration
Security & OS
Tamper detection, Linux-based device security, Shell scripting
Backend Development
Languages
Python, Java, JavaScript, TypeScript
Frameworks & APIs
Django, Flask, REST APIs, tRPC
Databases & ETL
PostgreSQL, MySQL, Apache NiFi (ETL pipelines)
DevOps & Cloud
Tools
Docker, Ansible, Git, Bitbucket Pipelines
Cloud
AWS (Certified Solutions Architect – Associate), Vercel
Monitoring
Grafana, Prometheus, ETL pipelines
Experience
Building intelligent systems at the intersection of AI, computer vision, and IoT infrastructure.
Cognitive Systems
Senior Software Engineer
- Researched, benchmarked, and deployed multiple object-detection backbones (ConvNeXt, Faster R-CNN) for a live CCTV security platform, building a configurable model-selection layer enabling zero-downtime runtime switching between models.
- Built a behaviour analytics engine on top of object detections: implemented polygonal region-of-interest matching, contour tracking, and a loitering/directness displacement index driving a real-time rules engine for automated Telegram and cloud alert dispatch.
- Designed tamper-detection security software for Linux-based IoT devices; migrated GPIO I/O from Arduino/Raspberry Pi to Sonoff Wi-Fi Smart Switch, improving hardware reliability by over 50%.
- Engineered a multi-threaded event pipeline using bounded queues to decouple producers and consumers, with dedicated worker threads for persistence, rules evaluation, and hot model/rules reloading — improving system throughput and resilience.
- Designed and deployed a CI/CD infrastructure using Docker and Ansible, enabling reliable automated delivery of security-critical software to client environments.
Cognitive Systems
Software Engineer
- Built a production asynchronous computer vision inference pipeline: buffered camera frames into queues, ran YOLOX/Keras models on background workers, and filtered/rescaled detections for real-time downstream alerting.
- Designed and implemented a rule engine scorer that ingests model outputs, applies time/region/tag rules, computes per-tag confidence scores, and emits actionable alerts with scheduling and activation tracking.
- Developed image classification and segmentation functions using MSE, SSIM, and OpenCV; implemented a correlation tracking algorithm using dlib; trained ML models using TensorFlow and Keras with YOLOv3 for object detection and annotation.
- Established MQTT message-brokering infrastructure (Mosquitto) between IoT devices and backend systems; built custom APIs delivering real-time AI-analysed image feeds to Telegram channels as part of a commercial security solution.
- Mentored graduate engineers in machine learning deployment, TDD, Docker, SQL, and Python best practices.
Featured Projects
A showcase of my professional work, community involvement, and personal projects that demonstrate my skills and passion for technology.
CCTV AI Security Platform
Production computer vision system for live CCTV security monitoring — multi-model object detection (ConvNeXt, Faster R-CNN, YOLOX), behaviour analytics engine with polygonal ROI matching, and real-time alert dispatch.
IoT Event-Driven Infrastructure
Designed MQTT message-brokering infrastructure (Mosquitto) between IoT devices and backend systems, with multi-threaded event pipelines and tamper-detection security for Linux-based IoT deployments.
Personal Website Evolution
Journey from Django-based portfolio to modern TypeScript-powered platform, showcasing growth in technical skills and design philosophy.
Let's Work Together
Ready to bring your ideas to life? I'd love to hear about your project and explore how we can work together.