Kingsley Akindele
Senior Software Developer & Product Thinker, Passionate about Design-Driven Engineering
Lagos, Nigeria
Actions
Kingsley Akindele is a Senior Full-Stack Engineer at Poptin, where he builds and runs the backend systems behind its products. He has spent the last eight years building production software, mostly on the backend, across legal tech, marketing tech and Web3.
Before Poptin, he was Engineering Manager at LawPavilion, leading a team of 20+ engineers, and he also served as Lead Backend Engineer at TowneSquare, running its infrastructure on Google Cloud. He is a core contributor to Solbase, a blockchain-based music streaming startup.
Kingsley has spoken at the Ethereum Nigeria Builders Meetup and judged the 3MTT Lagos Hackathon. He holds an MSc with Distinction in Computing and Information Systems from Liverpool John Moores University.
These days he spends most of his time on one question: how to take AI features from a demo to something real users can depend on.
Links
Area of Expertise
Topics
Shipping AI to Production: Backend Patterns, Cloud Deployment & Live Demo
Most AI demos look great on a laptop. The problems start when you try to put them in front of real users. Latency gets unpredictable, costs climb fast, the model times out halfway through a request, and suddenly your nice demo is a support ticket.
In this talk I'll walk through how I approach shipping AI features to production from the backend side. I'll cover the patterns that have actually helped me: handling long-running model calls with queues and background jobs, streaming responses so users aren't staring at a spinner, retries and fallbacks when a provider is slow or down, caching to keep costs sane, and basic guardrails around inputs and outputs.
Then I'll move to deployment. I'll show how I package and deploy an AI-backed service on the cloud (GCP), what I watch in terms of monitoring and logs, and the mistakes I've made along the way so you don't have to repeat them.
I'll finish with a live demo. I'll take a simple AI feature built with NestJS, deploy it, and show it running end to end.
I work on backend systems handling around 20M requests a day, so this comes from real production work, not theory. You should leave with patterns you can use on Monday.
Beyond the Prototype: End-to-End AI Engineering for Modern Agents
⭐ Shipping AI to Production: Backend Patterns, Cloud Deployment & Live Demo
A practical, end-to-end session on taking AI from prototype to production. We’ll cover proven backend patterns for integrating AI into real systems, strategies for deploying on the cloud, and best practices for scalability, monitoring, and reliability—ending with a live demo of a production-ready AI service in action.
⭐ Beyond the Vector: Architecting Multimodal Graph RAG with ADK & Memory Bank
Most AI agents fail in production because they lack context and continuity. When the user says, "Fix that diagram I showed you last week," standard RAG breaks. This session dives into a production-grade stack on Google Cloud to solve the three pillars of agency: Perception (Gemini), Structure (Spanner Graph), and Identity (Memory Bank). We will walk through building an agent using the ADK that performs multi-hop reasoning across unstructured visual data and structured graph nodes. You'll learn how to implement an evolving Memory Bank that de-duplicates user insights in real-time, turning stateless chat into a stateful, intelligent partnership.
DevFest Warri 2026 Sessionize Event
Kingsley Akindele
Senior Software Developer & Product Thinker, Passionate about Design-Driven Engineering
Lagos, Nigeria
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top