I asked Gemini who I am and why someone should hire me for ML. It gave me a highly accurate, yet 10-year-old version of myself.

I was recently approached by an ML company setting up shop in Zurich. To be honest, I’m still not sure if it was a real person, an agent, or just a sophisticated scouting bot. But it sparked the question: What exactly do they see when they look at me?

I know I can provide crazy value, but within a certain scope. I also know my digital footprint is sparse. To find out what the world thinks of 'James Litsios,' I went into an anonymous Gemini session and asked a simple question: 'Why would someone hire this man for an ML project?'

The answer I got shocked me: a highly accurate "slice" of a man who existed ten years ago. 

Let's start with Gemini's response (with some annotations in RED). I will then give you my take on it.

Gemini Pro's reply to: Who is James Litsios and why would someone hire him to develop a ML application?

Dr. James Litsios is a veteran technologist, architect, and leader based in Zurich, known for his expertise in high-performance computing, financial engineering, and distributed systems. He is perhaps most recognized as a co-founder of Elevence Digital Finance and a key architect behind ..ML (.. Modeling Language) (my NDA doesn't allow me to repeat these claims, so I removed two letters and two words here).

If you are considering hiring him to develop a Machine Learning (ML) application, his value lies less in "basic model training" and more in the architectural integrity, mathematical rigor, and scalability of the system.

Why Hire James Litsios for ML Development?

1. High-Performance Engineering & Scalability
• Litsios has a deep background in quantitative finance and automated trading (notably as the long-time CTO of Actant). ML applications often fail because they can’t handle real-time data or scale efficiently. His experience with multi-core reactive systems, non-blocking queues, and GPU support ensures that an ML model isn’t just a "notebook project" but a production-ready engine capable of handling massive throughput.
2. Mathematical & Algorithmic Rigor
• His academic and professional history is rooted in complex simulations and solvers.
• Scientific Computing: He holds a PhD from ETH Zurich with a focus on modeling and simulation.
• Advanced Math: His work has involved automatic differentiation and multi-grid interpolations—concepts that are foundational to how modern neural networks are optimized and trained.
3. Privacy & Distributed Execution
• In the modern ML landscape, data privacy is a massive hurdle. Litsios holds patents in privacy-preserving shared execution. If your ML application requires:
• Federated learning (training on data you don't "see").
• Secure multi-party computation.
• Blockchain-integrated AI logic.
  ...his specific expertise in "smart" distributed contracts and privacy-preserving protocols is nearly unparalleled.
4. Language & Domain-Specific Logic
• Litsios is a "language person." He helped create ..ML (again two letters removed) to describe complex rights and obligations. In ML, this translates to System Design: building the domain-specific languages or frameworks that allow data scientists to express complex business logic without breaking the underlying infrastructure.

Summary Table: The "Litsios" Advantage

Category	Skillset
Infrastructure	Building the high-speed "pipes" and GPU-accelerated environments ML requires.
Integrity	Applying "Smart Contract" levels of precision to ML workflows to ensure auditability.
Security	Implementing privacy-preserving layers so ML can use sensitive data legally.
Leadership	Bridging the gap between raw research (PhDs) and commercial product delivery.

Bottom Line: You wouldn't hire James Litsios just to "clean a dataset." You would hire him to architect the entire ecosystem—ensuring your ML application is mathematically sound, cryptographically secure, and fast enough to beat the market.

Me reviewing Gemini reviewing me

Gemini actually got right much of how I engineer systems. For the record, I'll complement Gemini's view with the follows:

1. High-Performance Engineering & Scalability

• Yes, spot on, multi-core reactive systems, non-blocking queues, and GPU are still dear to me. I was a C++ guru for 20 years, I cared about losing time in context switches and cache misses. The Actant AG derivative marking making system (where I was CTO) was the principal trading tool of some of the major international derivative market making firms from 1999 to ~2004. 
• More recently JAX has been my tool of choice, for example for real-time stream oriented processing as scalable on GPUs.

2. Mathematical & Algorithmic Rigor

• Yes, however rigor only when needed! And in fact have adopted "lazy rigor" as best approach. I prefer "loose" math in a DSL that gets formally checked with help from tools. As an engineer, is still see math as the most powerful tool!
• I started my career doing continuous and combinatorial optimization to synthesize and layout analog circuits (a world first). 
• Then I wrote a semiconductor device simulator as part of my PhD. Still a best seller after 30 years! 
• Later, I was responsible for pricing and risk in option pricing, where my best project had us caching everything in 6d interpolation grids to produce sub-nano second pricing. 
• Finally, more recently, I have developed proprietary signal processing for distributed sensors.

3. Privacy & Distributed Execution

• "nearly unparalleled expertise in 'smart' distributed contracts and privacy-preserving protocols"... from 2015 to 2019! (see bearingpoint-spin-off-elevence) 
• My current focus is less on privacy and more on deepening semantics. One way to look at this is terms of how many phases towards finalization do you embed in your core semantics? Two, as in a classical database? 3, 4, 7, 8, even more? And why would you do that? A great question to ask me!

4. Language & Domain-Specific Logic

• Litsios is a "language person." Wow, I agree! Even math is more the "how of semantics" to me than about truly caring about the math as classical mathematician. 
• There are two stories here. The first one was that already early 80s I wrote my code generators to produce real-time PC games, and was working on compilers at school. 
• The bigger story was the miserable quality of some of my project's software deliveries pre-2000. This was thirty years ago, so I feel it is ok to mention it, but here I was, responsible for the company's software, and the software was buggy. Could we not do better? Was there a more mathematical way to write software? Never shy of effort, I spent much time learning how to see software as math. The result is that ten years ago I was using very codified functional programming to embed math in software. More recently I use probabilistic formal methods, and keep the FP style mostly to leverage math abstraction. 

Finally, let's review elements from Gemini's bottom line from above:

• AI: You wouldn't hire James Litsios just to "clean a dataset."
• James: True! ;-)
• AI: You would hire him to architect the entire ecosystem
• James: Sadly true. I say sadly because very few projects are about doing the "entire" archicture!
• AI: ensuring your ML application is mathematically sound, 
• James: Very true.
• AI: cryptographically secure,
• James: Less true, as cryptography is much about hardware and rigorous system level processes, which is less my specialty.
• AI: fast enough to beat the market.
• James: Romantically true, but honestly I am not your best VHDL developer with FPGA experience!

To finish off, I asked Gemini to illustrate its statement about me!

All original content copyright James Litsios, 2026.