Former academic with a PhD in Information Science at the intersection of philosophy and musicology.

Currently contributing as AI Safety Red Teamer (contract) at Mercor, conducting model output comparisons and flagging for RLHF annotations to identify biases and vulnerabilities in frontier AI safety projects.

┈

For the last 15 years, I've studied belief systems, symbolic cognition, aesthetic structures, and the philosophy of interpretation—first in academia, now for AI models. Leveraged PhD research in information theory and music semiotics for multimodal data labeling (audio-text alignment, emotion/expressive annotation) and ethical red-teaming. Applied symbolic cognition to DeFi protocol analysis (Aave/Compound since 2020), informing AI ethics in decentralized systems.

┈

Specialize in high-depth multimodal and ethical annotation: • Metaphysics, ideology critique, ritual, metaphor • Music semiotics, aesthetic reasoning, symbolic systems • Cultural datasets, emotion labelling, audio-text alignment

Comfortable with complex reasoning traces, red-teaming, prompt evaluation, and data curation in philosophy, arts, and humanities domains.

┈

Also a DeFi native (Aave power user since 2021), UT Austin coding bootcamp 2023 graduate, and lifelong classical guitarist.

┈

Available for remote-only, flexible expert work: – AI safety/red-teaming & ethics evaluation – Multimodal annotation & prompt engineering – AI training (humanities/multimodal) – Crypto/DeFi specialist support

Prefer async, low-meeting roles. Rate $50–200/hr (negotiable).

Currently reading Plotinus and teaching one remaining classical-guitar student who found me by synchronicity.

Open to interesting projects. DMs welcome.