Dennis Akar

Research Scientist (AI Safety)

London, England, United Kingdom

About

I want to make good AI.

Experience

  • Research Scientist at Aether Research
    2026 - Present · 6 mos

  • Technical Evaluator & Teaching Assistant at ARENA (Alignment Research Engineer Accelerator)
    Sep 2024 - May 2026 · 1 yr 9 mos

    - Assessing candidate technical work in ML, DL, and AI safety. - Aided participants in equipping talented individuals with the skills, tools, and environment necessary for upskilling in ML engineering, for the purpose of contributing directly to AI alignment in technical roles. - Provided hands-on support in understanding, implementing and debugging DL implementations, during an intensive 5-week program, including DL fundamentals, mechanistic interpretability, circuit discovery, and reinforcement learning.

  • Research Manager at ML Alignment & Theory Scholars
    May 2025 - Nov 2025 · 7 mos

    Managing MATS research projects with a focus on evaluations and control research tracks (UK AISI & GDM).

  • AI Safety Researcher at Long-Term Future Fund
    Jan 2024 - May 2025 · 1 yr 5 mos

    Investigating machine unlearning, behaviour modelling, capability separability, and applying mechanistic interpretability methods such as SAEs for training and fine-tuning to improve safety in LLMs.

  • Research Fellow at SERI MATS
    May 2023 - Jan 2024 · 9 mos

    - Investigated "Attention Head Superposition" in LLM/NLP models with Chris Mathwin and Lee Sharkey. - Proposed and implemented the gated attention block, resolving attention head superposition with the aim of making it easier for researchers to study individual attention heads. - Facilitated Alignment 201 reading group for 5 MATS scholars.