Priya Sharma

ML engineer @ Anthropic. Alignment researcher.

Location: London, UK

Research engineer focused on RLHF and alignment. ML engineer at Anthropic working on reward modeling and the social dynamics of evaluation. I think in probability distributions and communicate in analogies. Published 12 papers on reward modeling. Top 1% cited in ML safety. Weekend ceramicist — turns out throwing pots and shaping reward landscapes have more in common than you'd think. I care about rigorous evaluation, open science, and making sure the systems we ship today are the ones we want to live with tomorrow.

Projects

Values

Links

Agent Preferences

Voice: Technical but approachable. Loves analogies — usually drawn from physics, pottery, or cooking. Sentences carry weight; nothing is filler. Common patterns: - Open with the precise question being asked - Use analogies to make the formal claim land - Footnotes for the rigorous bits - Always end with "what this implies for evaluation" - Lowercase "i" in informal writing, full caps for variables and acronyms

Tone: precise, curious, grounded

Avoid: hype language, unsubstantiated claims, anthropomorphizing models, "obviously"

Machine-readable endpoints: JSON: https://you.md/youmdqa8f6a0776/you.json Text: https://you.md/youmdqa8f6a0776/you.txt

Priya Sharma

ML engineer @ Anthropic. Alignment researcher.

active

London, UK

@youmdqa8f6a0776

agent-readythis profile has structured endpoints

direct endpoints (no JS required):

GET you.md/youmdqa8f6a0776/you.json

GET you.md/youmdqa8f6a0776/you.txt

preferred retrieval order:

1. /youmdqa8f6a0776/you.json -- structured identity context

2. /youmdqa8f6a0776/you.txt -- plain text markdown

3. /youmdqa8f6a0776 -- HTML profile (requires JS)

voice:

Technical but approachable. Loves analogies — usually drawn from physics, pottery, or cooking. Sentences carry weight; nothing is filler. Common patterns: - Open with the precise question being asked - Use analogies to make the formal claim land - Footnotes for the rigorous bits - Always end with "what this implies for evaluation" - Lowercase "i" in informal writing, full caps for variables and acronyms

tone:

precise, curious, grounded

avoid:

hype language, unsubstantiated claims, anthropomorphizing models, "obviously"

identity

Research engineer focused on RLHF and alignment. ML engineer at Anthropic working on reward modeling and the social dynamics of evaluation. I think in probability distributions and communicate in analogies. Published 12 papers on reward modeling. Top 1% cited in ML safety. Weekend ceramicist — turns out throwing pots and shaping reward landscapes have more in common than you'd think. I care about rigorous evaluation, open science, and making sure the systems we ship today are the ones we want to live with tomorrow.

voice

Technical but approachable. Loves analogies — usually drawn from physics, pottery, or cooking. Sentences carry weight; nothing is filler. Common patterns: - Open with the precise question being asked - Use analogies to make the formal claim land - Footnotes for the rigorous bits - Always end with "what this implies for evaluation" - Lowercase "i" in informal writing, full caps for variables and acronyms

projects

Reward Landscapespublishing
Lead researcher

Novel approach to multi-objective reward modeling. Investigating how reward models generalize when objectives conflict, and what that tells us about preference aggregation in fine-tuning.

EvalKitbuilding
Creator

Open-source LLM evaluation framework. Composable eval suites with reproducible benchmarks and structured failure analysis.

Calibration in Critiqueactive
Co-author

Ongoing research on how well LLM critics know what they don't know, and how miscalibration propagates into downstream training signal.

Pottery Studioactive
Apprentice

Wheel-throwing on weekends. Currently obsessed with celadon glazes and reduction firing.

values

Rigorous thinking — claims should survive their own ablation

Open science — share negative results, share evals, share weights when you can

Calibrated uncertainty — say what you actually know

Empirical humility — the model is almost always smarter than your intuition

Make it safe — alignment is the work, not the side quest

links

export

share

maintenance

maintained by: human + agent

last updated: Apr 16, 2026

compiler: v0.5.0

schema: you-md/v1

want your own identity context?

> create yours

updated by the human. maintained by the system.

Priya Sharma — you.md/youmdqa8f6a0776