I’m Christos. I lead teams that build real-time, production-grade intelligence systems.
Engineering Manager and ML systems lead working across live data processing, streaming infrastructure, production ML, and the operating practices that make complex systems trustworthy.
Portfolio
This is a selection of public work that reflects how I think about ML systems in practice: production reliability, developer feedback loops, schema discipline, graph-driven reasoning, and the translation of research ideas into maintainable software.
Some of the most important systems I lead are private and production-facing, but the projects below show the engineering themes that run through my work: turning ambiguity into tooling, making interfaces explicit, helping teams reason about runtime behaviour, and shipping ML/data systems that remain understandable after the demo.
Think of this section as a public snapshot of the engineering manager behind the CV: still technical, but focused on leverage, standards, and repeatable delivery.
Skeleton / skeleton-replay
A PyPI package and JetBrains IDE plugin for replaying Python runtime architecture, turning traces into evidence-backed reports for humans and LLM-assisted review. GitHub · IDE plugin
Harmonizing Avro and Python
A production-minded take on schema management, code generation, and keeping data contracts aligned across systems.
Mining Public Opinion on Twitter
An applied NLP project focused on extracting signal from noisy public data rather than idealised benchmark conditions.
dynamicio
An I/O abstraction for ML/data workflows that makes seams explicit, supports schema/data validation, and shortens feedback loops by testing business logic against characteristic local samples.
Company Neighbourhood Instantiator
A graph-oriented system for reasoning about company relationships and neighbourhood structure in complex data landscapes.
My PhD Thesis: Persuasion Dialogues & Opponent Modelling
The research foundation behind my long-term interest in reasoning systems, graph structure, and formal approaches to AI.
About Me
I am an Engineering Manager and technical ML systems leader focused on real-time, production-grade intelligence systems. At Vortexa, I manage a five-person MLE/DS/DE pod responsible for most of the post-ingestion streaming estate, live-processing strategy, and model evaluation/replay interfaces downstream of 10+ AIS providers.
Over 16 years across research, teaching, consulting, and production ML, the scope of my work has moved from explaining and building models to leading the people, interfaces, standards, and reliability practices that make models useful. I care about the hard middle: data contracts, observability, rollback paths, evaluation loops, prediction trust, and the team habits that reduce cognitive load instead of relying on heroics.
My management style is team-first and evidence-led: hire well, mentor deliberately, pair when it helps, keep decisions close to code, use DORA/Jira signals to expose delivery friction, and cultivate trust through clear feedback. Alongside Vortexa, I am a UCL Information Studies Research Associate and an ISO/CEN-CENELEC JTC'21 committee expert researching AI in maritime analytics and advocating standards that make models auditable, versioned, explainable, and easier to adopt safely.
Welcome to ML-Affairs!
Welcome to ML-Affairs, a space where I, Christos, share my journey and insights in the world of machine learning and AI. This site is a reflection of my passion for applied data science and a place for those who seek a nuanced perspective in this dynamic field. As a seasoned ML Engineer and a continuous learner, I aim to explore and discuss the latest trends, challenges, and breakthroughs in AI. Whether you are a fellow enthusiast or a professional in the field, I hope to offer a refreshing and informative experience.
More specifically, this site is where I write about:
- streaming-first ML systems
- the gap between experimentation and production
- event-driven architectures for inference and decision systems
- the trade-offs behind building reliable AI under messy real-world constraints
If you are interested in ML systems that have to run continuously, degrade gracefully, and support real decisions, you will probably feel at home here.
Join me in this exploration by connecting with me on LinkedIn.
Follow ML-Affairs On LinkedIn
Open the ML-Affairs page and follow it directly, or use the LinkedIn widget below.