{"slug":"synthlabs","name":"SynthLabs","website":"https://synthlabs.ai","tagline":"Post-training research: synthetic data and scalable RL alignment","description":"SynthLabs is a post-training research company combining RLHF with synthetic AI feedback (RLAIF) to build scalable alignment and reasoning pipelines, publishing open research and datasets used in RL post-training.","domains":["machine-learning","alignment","rlhf"],"locations":["San Francisco"],"founders":[{"name":"Louis Castricato","xHandle":null},{"name":"Nathan Lile","xHandle":null}],"teamSize":"1-10","funding":"Seed (M12 and First Spark Ventures, 2024)","raising":null,"founded":2023,"notable":"Team includes founders of the trlX RLHF library","entityType":"Data + environments","canonicalUrl":"https://envindex.com/startup/synthlabs","research":null,"sources":[],"capabilityCatalog":{"startupSlug":"synthlabs","reviewedAt":"2026-08-16","status":"cataloged","items":[{"name":"RLHF and RLAIF Research","kind":"Research program","summary":"Post-training research spanning human and AI feedback.","access":["Public / Open"],"sourceUrl":"https://www.synthlabs.ai/research","sourceLabel":"Research","verificationStatus":"company-reported","lastVerified":"2026-08-16"},{"name":"Generative Reward Models","kind":"Research program","summary":"Research on generative reward modeling.","access":["Public / Open"],"sourceUrl":"https://www.synthlabs.ai/research/generative-reward-models","sourceLabel":"Generative Reward Models","verificationStatus":"company-reported","lastVerified":"2026-08-16"}]},"artifacts":[],"caveat":"Legacy profile awaiting claim-level source migration"}