08/30/2026 updated
100 % available
Freelance Computational Engineer | ML, Simulations & Robotics
Nicosia, Cyprus
Worldwide
B.Sc. Physics, TUMAbout me
I'm a computational engineer. I work at the intersection of physics, engineering, and software, on problems that don't have an off-the-shelf answer: machine learning pipelines, robotics control systems, numerical simulations.
AI AgentsArtificial IntelligenceComputer VisionAutonomous SystemC++ (Programming Language)Computational Science and EngineeringComputer SimulationPython (Programming Language)Machine LearningRobotics Design and ProductionRobotic Automation SoftwareSimulationsRust (Programming Language)Robot Operating SystemMobile Robots
A lot of my work is machine learning applied to physical targets: detecting and tracking objects that are small, distant, or easily confused with something else, and building the models that separate the two reliably. The hard part is rarely getting a model to work. It is getting it to work on a particular edge case, the smallest object, the hardest frame, the one a weaker model misses.
Robotics is the second biggest part of what I do. I build the software that runs on the robot itself, not just around it. That means writing the perception, localization, and control code that lets a machine navigate somewhere hazardous, decide what it is looking at, and act on it, often on constrained edge hardware where every millisecond and every watt is a real limit.
I also build systems that are meant to run without me watching them. An autonomous pipeline is only useful if you can trust it to make the right call unsupervised, and that trust has to be earned through engineering. I care about the same thing when I write physics simulations: a finite element model is worth nothing if it does not display verifiable behavior.
For more information on what I do, see my website: https://intellycode.dev
Experience
Professional experience0 - 5 years
Freelancer since2025
Languages
GermanFluentEnglishNative speakerGreekNative speakerRussianNative speaker
Project history
Built a cold outreach system trusted to act on its own, unsupervised. Maintains high level of personalization while running completely autonomously.
Got a neuromorphic gesture-recognition board driving a third-party robot. Built the hardware to supply the external processing unit, set up the networking and communication between the robot and the processing unit, and wrote the ROS layer turning recognized gestures into robot actions. Control ran on a timing-based approach and lidar-based obstacle avoidance kept it from colliding.
Built a detector and tracker for an early-stage deep-tech company's target object, so they could rely on the system precisely where it is hardest to trust: spotting the smallest, most distant instances, the ones a weaker model misses first. The new model beat the published baseline there by 16%, and the classifier I added kept that performance while telling the target apart from three classes of lookalikes, plus motion prediction so the tracker keeps a live estimate running between observations.