Aarav Mehta
@aarav-mehta
ML eng @ ex-Scale AI · building eval tooling for LLMs
San Francisco, CA17 followers·12 following7 events
Spent 3 years labeling and evaluating LLM outputs at Scale AI before going indie. Now building Evalify, a structured benchmark runner for frontier models. Passionate about making evals reproducible and shareable.
Building now
Evalify – open-source LLM benchmark runner with shareable leaderboards
Skills
PyTorchPythonLLM EvalsFastAPITypeScript
Open to
cofounderfunding