Yannic Muskalla

he/himYannic Muskalla

Master’s Student
Researcher

DFKI – Neuro-Mechanistic Modeling

RAIME – Responsible AI and Machine Ethics

Saarland Informatics Campus

Campus D3.2 (DFKI), Room +2.08

66123 Saarbrücken

Germany

About Me

As a researcher in the Responsible AI and Machine Ethics (RAIME) group, I work at the intersection of computer science and philosophy, with a particular focus on AI alignment and human oversight. My current research investigates how formal theories of reasons can be used to guide and align reinforcement learning agents.

Interests

  • AI Alignment
  • Causal Explanations
  • Causal Abstraction
  • Analytical Philosophy
  • Computational Type Theory

Education

  • M.Sc. in Computer Science, ongoing

    Saarland University

    Reimbursement Machines for Reason-Aligned Reinforcement Learning

  • M.A. in Philosophy, 2025

    Saarland University

    Causal Explanations and Epistemic Relativization

  • B.A. in Philosophy, 2022

    Saarland University

    Computation Type Theory for Philosophers: A Case Study for the Feasibility of Mechanization

Teaching (9)

  • Formal Methods for AI Alignment

    Lecturer (English), in Summer 2026
    Seminar at Saarland University

  • Reinforcement Learning

    Assistant (English), in Winter 2025/26
    Lecture at Saarland University

  • Ethics for Nerds

    Tutor (English), in Winter 2024/25
    Lecture at Saarland University

  • Ethics for Nerds

    Tutor (English), in Summer 2024
    Lecture at Saarland University

  • Seminar Kausalität

    Student Assistant, in Summer 2024
    Seminar at Saarland University

  • Ethik der Digitalisierung

    Tutor, in Winter 2023/24
    Saarland University

  • Ethik der Digitalisierung

    Tutor, in Summer 2023
    Saarland University

  • Erkenntnistheorie

    Tutor, in Winter 2021/22
    Saarland University

  • Erkenntnistheorie

    Tutor, in Winter 2020/21
    Saarland University