Alexander Amin

Engineer · Founder · Speaker

I build software, mostly with AI these days. 12+ years across full-stack engineering, enterprise partnerships, and pre-sales. Active in the Google Developer Groups community and occasional conference speaker.

Based in Frankfurt.

Alexander Amin

About

About Me

I'm Alex, a software engineer and founder based in Frankfurt. I've been building production software for 12 years, the last two focused on AI.

Right now I'm working on AI pipelines that process video and audio at scale, building with Gemini, Claude, and Vertex AI. Before that I spent three years managing technical partnerships at ARD Mediathek, working with Google, Amazon, and Deutsche Telekom. Before that I ran pre-sales engineering at a startup. Before that I founded a software consultancy at 19, grew it, and it got acqui-hired.

I give talks about AI at conferences (DevFest Hamburg, GDG Lisbon, Hannover Messe 2021), taught at Frankfurt University of Applied Sciences (2023–2024), and co-organized a hackathon with Google and Lufthansa. I've won 7 hackathons, which mostly means I'm good at building things fast and presenting them to strangers.

I speak German, English, Spanish, Portuguese, and some French, Dutch, and Dari. My Duolingo streak is past 1,700 days, which is either impressive or concerning depending on your perspective.

Lecturer

Frankfurt University of Applied Sciences

Speaker

Google Developer Groups, Tech Meetups

Experience

Siemens, Vodafone, ARD

Work

Featured Projects

Agosto

The Discovery Layer Between Social Content and AI Agents for Restaurants.

Agosto makes restaurants visible to ChatGPT, Gemini, and Perplexity by turning scattered social content into structured data AI can actually read. The platform connects restaurants with food creators through an automated attribution system — creators drive discovery, restaurants only pay for new guests. Built on 4 years of production-grade reservation infrastructure handling thousands of bookings monthly, Agosto bridges the gap between where people find food (TikTok, Instagram, AI) and where they book a table.

NuxtNode.jsGoogle Cloud RunMongoDBCloudflare

RaumRadar

An app built out of love for traveling and working remotely

For a while now, I had wanted to build an app to help me remember which coworking spaces or cafés I most liked in different cities around the world. RaumRadar helps me keep track of these with more details than I could on Google Maps

Gemini Kicks & Llama Hoops

A Comparative AI Analysis: Pitting Google Gemini vs. Meta Llama for Real-Time Video Highlight Generation.

To test the real-world capabilities of leading AI models, I built two parallel projects that automatically analyze and clip highlight moments from full-length sports games. This exploration into multi-modal AI showcases a practical application of Gemini and Llama 4 for automated content creation, directly comparing their performance on a complex, real-world task. Both projects are open-source.

PythonffmpegGoogle Gemini APIGoogle Cloud TTSMeta Llama 4Groq

Railmap for OpenRailwayMap

An Android App for Railway Enthusiasts.

A native Android app offering a clean, mobile-native interface for the extensive data from OpenRailwayMap. Published and available on the Google Play Store.

KotlinAndroid SDKMapbox GL

Speaking

Talks & Presentations

I believe in building a stronger developer community by sharing knowledge and insights from real-world projects. I enjoy breaking down complex topics related to AI and cloud architecture for technical audiences.

DevFest Hamburg 2025

"Demystifying Agents"

Understand AI agents like never before by learning to build one from the ground up using just the google/genai library and Firestore. Discover that agents are more accessible than you think and explore how the Agent Development Kit (ADK) can significantly streamline your workflow.

GDG Lisbon & Lagos

"Building Generative, Streamed UIs with the Gemini API and Vue.js"

Explored how to use structured output from LLMs to reliably generate deterministic JSON, preventing application failures and enabling real-time UI rendering.

Meta LlamaCon, San Francisco

"Project Showcase: Llama Hoops"

Demonstrated a practical, multi-modal application of Llama 4 for automated video content creation in a high-pressure hackathon environment.

Interested in having me speak at your event? I'm always open to new opportunities.

Let's Talk

Contact

Let's Build Something Together

I'm always curious about projects, new challenges and speaking opportunities. If you have an interesting topic, let's connect.