Julian Schulz

Curriculum Vitae
mail@julianschulz.eu|julianschulz.eu
LinkedIn|github.com/wusche1|Google Scholar

Work Experience

Oct 2025 – present
AI Safety ResearcherMeridian Visiting Researcher Programme
Cambridge
Research on LLMs learning encoded reasoning during RL. Supported by a grant from Coefficient Giving.
Nov 2024 – Jun 2025
Machine Learning EngineerAlexander Thamm GmbH
Berlin
Developing and deploying multi-agent systems; managing cloud infrastructure with Terraform.
Apr 2024 – Jul 2024
AI Safety ResearcherCoefficient Giving Grant
London
Independent AI safety research on Sleeper Agents and Automated Feature Labeling.

Publications

Sep 2026
Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard
Julian Schulz, Lukas Fülle, Rieke Fruengel·NeurIPS 2026 Workshop AI4GOODORAL
Feb 2026
Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning
Julian Schulz·COLM 2026 Workshop AdvML-Frontiers x CoTMA
Oct 2025
A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring
Julian Schulz·AI & Societal Robustness ConferenceBEST POSTER AWARD
Mar 2025
Automated Feature Labeling with Token-Space Gradient Descent
Julian Schulz, Seamus Fallows·ICLR 2025 Workshop Building Trust
Dec 2023
Steering Llama 2 via Contrastive Activation Addition
Nina Panickssery, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, Alexander Matt Turner
ACL 2024OUTSTANDING PAPER AWARD

Teaching & Mentoring

Jul 2025 – present
ML4GoodHead Teacher
Europe, Canada, Singapore & South Africa
Teaching and organizing the teaching team at 1 week AI-safety bootcamps.
Apr 2026 – present
Iliad IntensiveTeacher
Teaching Mechanistic Interpretability (Apr, Jun, Sep 2026) and Intro to ML Engineering (Jun, Sep 2026).
Apr 2026 – Jul 2026
SAIGE IncubatorResearch MentorSafe AI Germany
Remote
Mentored the team behind the steganography paper above (NeurIPS 2026 workshop, oral).
2025, 2026
MARSResearch MentorMentorship for Alignment Research Students
Cambridge
Mentored research teams in MARS 2.0 and MARS V.

Fellowships & Training

Jan 2024 – Feb 2024
ARENAMachine Learning BootcampAlignment Research Engineer Accelerator
Remote
Jun 2023 – Sep 2023
MATSResearch on Activation AdditionML Alignment Theory Scholars Program
Berkeley
Under the mentorship of Alex Turner.

Education

2021 – 2024
M.Sc. Biophysics and Complex SystemsGöttingen, Max Planck School Program
Grade 1.6·Transcript
2017 – 2022
B.A. Philosophy & PhysicsGöttingen
Grade 1.3·Transcript
2017 – 2021
B.Sc. PhysicsGöttingen
Grade 1.5·Transcript

Scholarships

2021 – 2024
Full Master’s ScholarshipMax Planck School of Matter to Life
2018 – 2024
Merit-based ScholarshipStudienstiftung des deutschen Volkes

Skills

Programming
Advanced Python (5+ years), Terraform, Azure, Claude Code
Machine Learning
PyTorch, RL (TRL, Tinker), W&B, Mechanistic Interpretability