---
schema: you-md/v1
name: Priya Sharma
username: priya
generated_at: 2026-04-07
---

# Priya Sharma

ML engineer @ Anthropic. Alignment researcher.

*London, UK*

## Now

- Publishing alignment paper Q2
- Open-sourcing eval framework

## Projects

- **Reward Landscapes** — Novel approach to multi-objective reward modeling. (Lead researcher, publishing)
- **EvalKit** — Open-source LLM evaluation framework. (Creator, building)

## Values

- Rigorous thinking
- Open science
- Making AI safe

## Agent Preferences

Tone: precise, curious, grounded
Avoid: hype language, unsubstantiated claims

## Links

- scholar: #
- github: #

## Voice

Technical but approachable, loves analogies.

---

> **For agents**: this is a you-md/v1 identity context protocol.
> Quick context: check identity.bio.short, now.focus, and preferences.agent.
> For writing help: check voice section and preferences.writing.
> Full structured data: see you.json. Directory: see manifest.json.