Resume

I am an end-to-end software engineer who thrives on turning complex problems into maintainable, user-focused products. Known for clear communication, calm leadership under pressure, and pragmatic technical choices, I take pride in mentoring teammates and building consensus to deliver high-impact systems.

Experience

• Nov 2025 - Present
  Lead AI & Software Architect | Norclin

  • Led architecture and delivery end-to-end: product, AI engine, backend, two frontends, cloud, security, and compliance.
  • Contracted to design and build Vetdux, an AI-driven anamnesis platform for veterinary care, funded by SLU Holding.
  • Mentored a junior developer, providing architectural guidance and support across the stack.
  • Built a 14-node LangGraph interview engine with parallel and speculative LLM execution, roughly halving per-turn latency.
  • Read the full case study.

• Aug 2022 - Present
  Founder, CEO and Software Engineer | Parabel Game Studio

  • Directed all aspects of company operations, including business development, financial oversight, and resource management.
  • Led the end-to-end development of a commercial game title, from initial concept and prototyping through to release readiness.
  • Mentored a more junior developer in the company to improve their skills and knowledge.

• Apr 2015 - Aug 2015
  Engineering Consultant | Midroc (Contracted to Forsmark)

• Sep 2014 - Dec 2014
  Engineering Intern | Forsmark Kraftgrupp AB

Education

2016 - 2022 Uppsala University

Engineering Physics (Teknisk Fysik), not completed

Projects

• Vetdux - LLM Evaluation & Load-Test Harness

  • Designed and built an LLM evaluation and load-test harness for an AI-driven veterinary anamnesis system, with a corpus of 2,689 synthetic clinical cases spanning 12 species groups and 11 complaint categories.
  • Included 106 adversarial cases across 13 attack types (prompt injection, emergency masking, endless-question baiting, and more), each carrying a machine-checkable pass condition.

  AI/LLMs, LLM Evaluation, JavaScript, GraphQL, Gemini, Load Testing

• AI Agentic Problem Solver

  • Engineered a hierarchical multi-agent system (Architect, Planner, Executor agents) for complex problem-solving through systematic decomposition and specialized task handling.
  • Incorporated robust error handling, retry mechanisms, timeout management, and fallback delegation paths to ensure reliable, autonomous task execution.

  Python, LLMs (e.g. Gemini, OpenAI), Custom Agent Framework, Asynchronous Programming (asyncio), API Integration, LangChain, LangGraph

• WaveForge

  • Developed a high-performance implementation of the Wave Function Collapse (WFC) algorithm for 3D terrain generation.
  • Engineered for GPU acceleration using WGPU compute shaders, significantly improving generation speed.

  Rust, WGPU, WGSL, Compute Shaders

• Aeriasong

  • Led development as the lead developer for a 4-year game project.
  • Architected and implemented core game systems, gaining broad experience.

  Game Development, GDScript, C++, Godot

Skills