From customer problem to production.

I’m Stratos Theodorou, a product-minded engineer and technical co-founder. I build cloud platforms, real-time data services and AI systems—and stay accountable for what happens after launch.

Athens, Greece. 15+ years in engineering, products & customer delivery.

Each dot is one WeatherXM station. The pulses are simulated.

  1. Understand the problem
  2. Design the system
  3. Build and deploy
  4. Stay accountable

Systems with a job to do.

From weather-station networks and energy forecasting to motorway tunnels: the most useful measure of a technical solution is what it enables the customer to do.

WeatherXM · real-time data

10,000 stations, streaming in real time.

Data platform, from proof of concept to production

I built the proof of concept and helped build the production platform that ingests real-time data streams from WeatherXM’s network of 10,000 weather stations: multi-instance ThingsBoard, Kafka and PostgreSQL. I also built the first Android app and the client-facing API on top of it.

From proof of concept to a 10,000-station network. The data foundation behind WeatherXM’s apps, API and data products.

Real-time ingestion, Kafka, ThingsBoard, PostgreSQL

ADMIE · energy

Data behind national grid balancing.

Independent engineering and cloud delivery

I independently designed, built and operated the weather-data backend used by Greece’s electricity transmission system operator to support balancing the national grid. I developed the Node.js services, messaging and document storage, provisioned the cloud infrastructure, and then migrated the system to Azure.

Two years in production. Ownership from application code to the cloud environment that ran it.

Node.js, message queues, document database, cloud migration to Azure

Fysiko Aerio · energy

A customer relationship built over a decade.

Technical delivery and ongoing customer ownership

Since 2016, I have been the sole owner of the customer relationship and technical delivery for Fysiko Aerio. I built and maintain the weather-data services the company uses for gas and electricity demand forecasting in Athens and Thessaloniki, working directly with the customer as its requirements evolve.

Ten years of continuity. Not just delivering a system, but understanding the customer’s needs and keeping it useful.

Customer discovery, weather data & APIs, long-term delivery

Olympia Odos · industrial IoT

From a tunnel at midnight to edge AI.

Edge systems, field deployment, data analysis and machine vision

For a jet-fan monitoring pilot, I built the RevPi gateway and cloud infrastructure: local time-series storage, on-device calculations and synchronization with ThingsBoard. I worked alongside colleagues installing and commissioning sensors overnight in motorway tunnels, then performed FFT-based vibration analysis and co-produced the customer report with a project partner.

The pilot led to a €200,000 project and helped establish the relationship and platform for a subsequent €300,000–€400,000 smart-camera situation-awareness project.

On the follow-on smart-camera project, I helped build the edge-to-cloud pipeline: machine-vision algorithms running on NVIDIA edge devices, streaming detection events to our cloud platform.

RevPi, ThingsBoard, time-series data, FFT analysis, edge machine vision

AI across the business. Not just inside the editor.

Leading practical AI adoption at WeatherXM: shared company knowledge, conversational requests and agents that can act across software, support and operations.

I recommended and helped implement Open Knowledge Format, the specification for our agent’s shared company knowledge base, and configured several of its integrations. The agent works in Slack, using company context to analyze support tickets and leads, gather requirements, collaborate with a specialist architecture agent, implement features and operate cloud infrastructure.

One software-delivery workflow

Slack, company knowledge, specialist agents

  1. 1

    Discuss

    Clarify the request and gather requirements with colleagues.

  2. 2

    Design

    Use shared context and an architecture agent to discuss the solution.

  3. 3

    Implement

    Write code, open a pull request and run automated code review.

  4. 4

    Release

    Apply approval requirements appropriate to the repository and change.

Low-risk content changesCompany website updates can go directly to production.

Sensitive backend changesA person reviews the pull request before it can be merged.

Customer support with an escalation path

Our Dify-based first-line support agent is retrieval-grounded (RAG) in help-desk documentation, historical support tickets and internal knowledge. Unresolved requests are escalated to a person. The broader company’s software work is now agent-led, across a portfolio of 160 repositories, with people responsible for direction and review.

New products, not just internal automation

I built our agent-facing weather API end to end with AI-assisted development, including pay-per-request data access for agents (x402), marketplace listings and automated cloud deployment. I also proposed a mobile AI assistant and led the hackathon teams: the assistant reached production within one month.

Explore the agentic weather API ↗

A builder’s path.

WeatherXM

Co-founder. Head of Engineering, 2021–2023; Chief Product Officer, 2023–2025; Founder & Builder, 2025–present.

Built the proof of concept and helped build the production data platform now streaming from 10,000 stations; built the first Android app and client-facing API. Created the Product & R&D team and led WeatherXM Pro’s product and design work.

Built a forecasting backtesting pipeline with a time-series foundation model (TimesFM) and evaluated ML weather models (GenCast, Aurora, AIFS ENS). Co-presented an AWS for Startups keynote in October 2025.

Ex Machina

Co-founder working across full-stack engineering, cloud infrastructure, UX and customer delivery. Built production data services, IoT pilots, edge machine-vision pipelines and integrations connecting commerce, ERP and logistics systems.

Led Meteoblue integration and cost-reduction work. Rebuilt exm.gr, generating pilot enquiries from customers who reported discovering EXM through ChatGPT or Claude.

Earlier foundations

Globo · Lead Android Developer · 2014–2015Hands-on enterprise-app development and leadership of six developers.

OpenCanvas · Co-founder, Android & Mobile UX · 2013–2014SDK, cross-platform UX and automated white-label app builds.

NCSR Demokritos · Research Associate · 2011–2013Transport and security applications for EU research projects.

Mobzili · Android & UI, part-time · 2011–2013Designed and developed 16 Android applications.

Tools in service of the outcome.

Solution design & product

Requirements discovery, architecture trade-offs, proofs of concept and pilots, customer demos, technical proposals and UX-led product design.

Cloud & distributed systems

Cloud infrastructure, cross-cloud migration, event-driven systems, messaging, caching and object storage. AWS / Cloudflare; earlier production work on Azure.

Software & integration

Full-stack web and mobile development, REST APIs, third-party integrations and GitHub-based CI/CD. TypeScript / Node.js and Java / Android.

Data

Real-time streaming and IoT ingestion at scale (10,000-station network; Kafka, MQTT, edge gateways); edge video-analytics event streams; PostgreSQL, MySQL and MongoDB in production applications (earlier Cosmos DB); SQL; data-lake querying and ETL (Athena, Glue); forecasting and signal analysis.

Applied AI

Knowledge-grounded (RAG) assistants, multi-agent workflows, tool and system integrations, risk-based human review. OpenClaw, Dify, Claude and Codex; currently exploring Azure AI Foundry.

Engineering and human-computer interaction

MSc, Human-Computer Interaction with ErgonomicsUniversity College London · 2010
Dissertation hosted by Sony Computer Entertainment Europe; awarded Distinction.

MEng, Electrical & Computer EngineeringAristotle University of Thessaloniki · 2008