Software engineer London, UK

ArtemSkulimovskiy.

Backend infrastructure.
Distributed systems. Applied AI.

I design and operate distributed calculation infrastructure at SimCorp. My main independent project is LitHarness, an AI system that plans, writes, and checks long-form fiction.

Previously Eigen Technologies and JPMorgan. MEng Computer Science, UCL.

01 / Selected work

Projects

All repositories

Agent execution environments

Anode

Anode architecture diagram: separate input sessions for a person and an agent on one Windows machine.

Gives an AI agent its own Windows desktop so it can use applications while you keep using your PC. Includes a live viewer, automation controls, and a virtual gamepad.

Separate input sessions, running as the same user with access to the same files.

  • C#
  • .NET
  • Windows APIs
  • MCP

Learned control & simulation

Haltere

20 September 2026: a scripted figure-eight with yaw assistance, beside live neural activity. This clip shows the published motor controller.

A connectome-constrained recurrent network trained to fly a drone in Liftoff. Its 30,000-neuron flight circuit uses fruit-fly connectivity, with learned parameters and a differentiable PyTorch simulator.

As of 22 September 2026, an experimental controller with visual race-cue assistance has completed three-lap races on two seen courses.

Research prototype. These results use explicit pilot assistance; completion on unseen courses and freestyle flight remain unproven.

  • Python
  • PyTorch
  • Differentiable simulation

Human–agent interaction

AgentUI

AgentUI interaction diagram: agent requests, browser controls, and structured responses.

Lets you guide a coding agent with forms, sliders, diffs, and live previews. Adjust the controls while the agent keeps working; it collects your decisions through MCP.

  • TypeScript
  • React
  • MCP
  • WebSockets

Desktop & graphics

Cathode

Cathode application screenshot with a CRT virtual monitor and picture controls.

Run real Windows applications on a virtual CRT monitor. GPU rendering adds phosphor pixels, scanlines, glow, and curved glass to live desktop content.

  • C#
  • WPF
  • GPU shaders

GPU simulation & artificial life

Primordia

A GPU artificial-life laboratory with five worlds and 42 presets. Physarum, Particle Life, Lenia, and reaction–diffusion are joined by Symbiosis, which couples agents and chemistry. Includes saved worlds, live measurements, and headless image and video export.

  • Rust
  • wgpu
  • WGSL

Preview of the four original worlds. Explore Symbiosis and the current presets in the repository.

More to explore

Agent perception & control

Ganglion

Helps AI agents react to screen changes and reach moving targets. Experimental fly-connectome motor commands are checked by a deterministic supervisor.

Language & agent experiments

Glossia

Explore branching language families, trace word ancestry, and compare communication protocols in controlled Codex and Claude experiments.

Developer tools

Unsung

Discover overlooked repositories through evidence from tests, releases, and documentation. Includes a command-line tool and a browser explorer.

More experiments (6 projects)

02 / Google Play

Android apps

Three educational quiz apps covering language and history.

Find them on Google Play
Language

Greek Letters Quiz

Learn the Greek alphabet through symbol recognition and alphabet-order quizzes.

View on Google Play
History

Medieval Armor Quiz

Identify historical armour through images, descriptions, and the periods it belongs to.

View on Google Play
History

Roman Emperors Quiz

Put a name to the portrait and explore the emperors and dynasties of ancient Rome.

View on Google Play

03 / Background

Experience

Connect on LinkedIn

At SimCorp, I architected and now operate a distributed calculation platform in production.

My work spans worker coordination, batch scheduling, the SQL data layer, and investigating failures across data and code. Previously, I worked at Eigen Technologies and JPMorgan, and founded an education startup.

MEng in Computer Science from UCL, specialising in AI.

Engineering with AI agents

I use Codex and Claude Code for implementation, debugging, and testing. I define the architecture and constraints, review changes, and verify results.

Technical toolkit

Production systems
Python · SQL · PostgreSQL · Docker · Linux
Independent projects
TypeScript · React · C# · Rust · PyTorch · MCP