Alexander F. Spies

AI Safety Researcher (PhD, Imperial College London) specializing in mechanistic interpretability and representation learning. Reverse-engineered causal world models in maze-solving transformers using SAEs, activation patching, and causal interventions. Shipped production LLM services (10k+ weekly queries); implemented scalable finetuning and evaluation infrastructure. Led collaborative research teams (9 researchers), published at NeurIPS/ICLR workshops, and open-sourced interpretability tooling. Deeply motivated by long-term AI safety; seeking to develop interpretability techniques that scale to frontier models.

Thesis: Interpretable Representations in Artificial Neural Networks

• Improved representations in Object-Centric Learning and reasoning
• Investigated failures and pathologies of multimodal foundation models
• Reverse-engineered world models in transformers using mechanistic interpretability techniques

• Thesis: Unsupervised World Models in the Animal-AI Environment
• Independent project: Neurosymbolic Learning & Neurally Weighted dSILP

• Completed graduate-level courses as an undergrad, alongside research

• Thesis: AI for the Automated Diagnosis of Atrial Fibrillation

Research engineer building infrastructure for production LLM systems at scale. (Promoted from intern to full-time in June 2025)

• Built scalable finetuning and evaluation infrastructure (UnSloth, SageMaker, vLLM, W&B); enabling systematic ablations and reproducible experiments across model variants.
• Shipped production LLM services (10k+ weekly queries); designed robust data pipelines and evaluation harnesses to monitor model behavior across diverse inputs.
• Developing agentic pipelines for multi-turn code generation with retrieval and tool-use.

Led independent research groups on mechanistic interpretability of "model organisms" of planning.

• Defined agenda on mechanistic interpretability for maze-solving LMs; trained transformers and Sparse Autoencoders, managed 9 researchers across 2 projects. Yielded 2 workshop papers and a best-poster award.
• Built SAE-based circuit analysis pipelines using activation patching, causal interventions, and feature visualization to reverse-engineer transformer internals; found interpretable causal world models.
• Research tooling and datasets made public and published in Journal of Open Source Software.

Carried out research on mechanistic interpretability of transformer internals and multimodal reasoning.

Provided technical guidance on AI Safety Research to 8+ Research Fellows

NeurIPS, ICLR, ICML, AAAI, UAI, AIJ; MATS Research Proposals (2024)