Backend Engineer & AI/ML Developer passionate about building scalable APIs, cloud systems, and LLM-powered applications. Sharing insights on Python, Django, FastAPI, LangChain, and deploying AI in production. I love writing about: Backend Engineering: Python, Django, FastAPI, REST APIs, Celery, PostgreSQL, AWS, Docker AI/ML Applications: LLMs, LangChain, Prompt Engineering, NLP, Vector Databases, MLOps Scaling Products: Payment integration, asynchronous systems, and performance optimization On this blog, I’ll share lessons learned, tutorials, and real-world case studies from my journey building production-ready backends and AI applications. My goal is to make complex concepts practical, actionable, and beginner-friendly — especially for engineers looking to move from theory to real-world deployment.
Hi, I’m Glory Kolade 👋 — a Software Engineer (Backend & AI/ML) with hands-on experience designing and deploying solutions that serve tens of thousands of users. At Excelmind (Lead Software Engineer), I led a team to build an EdTech platform that scaled to 50k+ students, teachers, and schools in its first year, with features like subscriptions, payments (Paystack), and exam practice APIs. At Digifigs (ML Engineer), I developed and deployed LLM-powered social media applications using ChatGPT API, Flask, LangChain, and AWS, fine-tuning models for real-world text generation tasks. At Insait (AI Engineer, Contract), I built conversational AI agents integrated into client websites, combining OpenAI APIs, Python, and graph data structures to deliver 24/7 intelligent support.
Sep 23, 2025 · 4 min read · When you build a machine learning system, the model gets all the glory. But for that model to do its job, it needs data—and that data needs to move. It flows from a database to a feature engineering service, from a prediction service to a user interf...
Join discussion
Sep 18, 2025 · 4 min read · When machine learning comes up in conversation, the focus almost always turns to models: the algorithms, the architectures, the breakthroughs. But models don’t learn in a vacuum. Their intelligence depends entirely on the data they’re trained on. In ...
Join discussion
Sep 1, 2025 · 4 min read · In the first article of this series, we looked at why the machine learning algorithm itself is only about 10% of the solution, and why a production-ready ML system is really about the bigger ecosystem that surrounds it. (find link to it here: https:/...
Join discussion
Aug 25, 2025 · 4 min read · When we talk about machine learning, it's easy to get fixated on the algorithms. We think of neural networks, logistic regression, or XGBoost. But the truth is, the algorithm is just a small piece of a much larger, more complex puzzle. A production-r...
Join discussion
Mar 21, 2025 · 3 min read · Part 1 of the "Building Trustworthy AI" Series Introduction Large Language Models (LLMs) are transforming industries, powering applications like support chatbots, content generation tools, and advanced data querying systems using Retrieval Augmented ...
Join discussion