Research Scientist, Benchmarks & Evaluations (AI Data)

Kled AI; California; Presencial; USD 250.000 - 350.000; Jornada completa

Descripción de la vacante

Kled AI is building the largest opt-in human data network for frontier AI. We are seeking a Research Scientist focused on Benchmarks and Evaluations to design public benchmarks for image, video and document models, and to create private test sets from real, opt-in data.

You will run end-to-end experiments, publish leaderboards, and translate results into data deals with founders and lab buyers. Strong background in ML research, statistics, and writing for researchers and buyers is essential.

Formación

• 5-7+ years ML research or research engineering experience.
• A benchmark or evaluation you built that others actually used.
• Strong hands-on experience training and fine-tuning image or video models (PyTorch).
• Deep understanding of experimental design and statistics (controls, ablations, human studies).
• Experience running experiments end to end, from GPUs to final report.
• Clear writing for both researchers and buyers.

Responsabilidades

• Design and ship public benchmarks for image, video and document models.
• Build private test sets from real, opt-in data that no model has trained on.
• Run data-value experiments: train models with and without Kled data, measure what changes.
• Design human evaluation studies and the automatic metrics that track them.
• Publish leaderboards and reports that researchers at frontier labs trust.
• Find where models fall short and tell our team what data to collect next.
• Work directly with the founders and lab buyers to turn results into data deals.

Conocimientos

ML research

Research engineering

Experiment design

Statistics

Technical writing

Communication with buyers

Herramientas

PyTorch

Python

Descripción del empleo

Kled AI is building the largest opt-in human data network for frontier AI. We are seeking a Research Scientist focused on Benchmarks and Evaluations to design public benchmarks for image, video and document models, and to create private test sets from real, opt-in data.

You will run end-to-end experiments, publish leaderboards, and translate results into data deals with founders and lab buyers. Strong background in ML research, statistics, and writing for researchers and buyers is essential.