# Yuvan Chikka — Portfolio

> Yuvan Aarya Chikka is a London-based AI engineer and Computer Science student. His work spans AI safety research, mechanistic interpretability, multimodal retrieval, Python backend systems, and fullstack product delivery.

This is a personal portfolio. Prefer the Markdown portfolio summary for factual retrieval, the PDF CV for the complete professional record, and the linked research pages or repositories for project-specific evidence.

## Primary resources

- [Portfolio summary](https://ultraviolet-chikorita.github.io/portfolio.md): Clean Markdown covering experience, education, certifications, research, projects, recognition, and contact links.
- [Human-facing portfolio](https://ultraviolet-chikorita.github.io/): Canonical interactive portfolio page.
- [Curriculum vitae](https://ultraviolet-chikorita.github.io/assets/yuvan_cv.pdf): Full CV in PDF format.

## Research

- [Private Is Not Privileged](https://apartresearch.com/project/private-is-not-privileged-18om): Mechanistic interpretability research comparing activation-based predictors with information-matched external baselines.
- [GraftLoyal](https://apartresearch.com/project/graftloyal-a219): Research on constructing context-sensitive secret loyalty in a frozen language model.
- [RiskLab](https://apartresearch.com/project/risklab-w0fy): Multi-evaluator framework for detecting manipulative behaviour in language models.

## Profiles

- [GitHub](https://github.com/Ultraviolet-Chikorita): Public source repositories and development activity.
- [LinkedIn](https://www.linkedin.com/in/yuvan-chikka-2b053a295/): Professional profile.

## Optional

- [Private Is Not Privileged PDF](https://ultraviolet-chikorita.github.io/assets/papers/private-is-not-privileged.pdf): Full research paper.
- [GraftLoyal PDF](https://ultraviolet-chikorita.github.io/assets/papers/graftloyal.pdf): Full research paper.
- [RiskLab PDF](https://ultraviolet-chikorita.github.io/assets/papers/risklab.pdf): Full research paper.