Skip to content
Research engineer — methodology

Reeya Patel

Research engineer at SquadProxy focused on LLM evaluation methodology, RAG pipeline infrastructure, and the statistical validity of multi-origin evaluation studies.

Eight years in ML infrastructure across two frontier labs and one large AI-adjacent startup before joining SquadProxy in early 2025.

Reeya leads methodology work at SquadProxy. The thread across her recent writing: evaluation that treats origin region as a first- class variable, not a confound. If you've read the multilingual benchmark post or the LLM evaluation use case, that's Reeya's framing.

Background

Before SquadProxy, Reeya worked on training-pipeline infrastructure at a frontier lab (2017-2023) and then led RAG systems at a production AI company (2023-2025). The specific scar tissue that produced the RAG-pipeline post was an early-2025 migration of a production index from single-origin to multi-origin collection that exposed the canonicalisation issues our proxy infrastructure for RAG pipelines post describes.

Writing on SquadProxy

What she's working on

Reproducibility tooling for multi-origin evaluation — a small set of helpers that turn "we ran the eval from 10 countries" into a reproducible artifact that a reviewer can re-run a year later and get numbers that mean the same thing. Expect a writeup in Q3 2026.

Contact

Reeya reads customer questions about evaluation methodology. The best path is hello@squadproxy.com with "methodology" in the subject line.

Ship on a proxy network you can actually call your ops team about

Real ASNs, real edge capacity, and an engineer who answers your Slack the first time.