NLP Benchmarking Scientist for AI Evaluation

Wintermeyer Ventures in San Francisco is seeking an experienced AI/ML researcher to join a research and engineering team building benchmarks and evaluation methods for advanced language models. You will evaluate models, develop benchmarks, scale evaluation pipelines, and publish findings while collaborating with labs and enterprise teams, with on-site work in San Francisco and visa sponsorship available.

The role requires 3+ years of research experience in NLP or benchmarking, strong Python