
Applied AI
Elif Demir
Research Scientist, Tidewater Labs
Istanbul
Elif Demir is a research scientist at Tidewater Labs, the research group inside the data platform Tidewater. She works on evaluating language models against real, messy work, and built the benchmark Tidewater uses to test whether a model can answer an analyst’s question from a real company’s tables rather than a tidy public dataset.
Elif wrote her doctorate on measurement error in survey data, which she describes as the same problem with fewer GPUs. She lives in Kadıköy, takes the ferry across the Bosphorus most mornings, and plays in a weekly board game group that takes itself far too seriously.
At Summit
Applied AI· Workshop · Advanced
Build an evaluation suite for an LLM feature in two hours


Elif Demir, Kenji Arai
Wed 9 June · 14:30–16:30Lab36 seats
Applied AI· Talk · Advanced
Your evals are lying to you: measuring models on real work

Elif Demir, Tidewater Labs
Thu 10 June · 11:40–12:20Studio






