Benchmarks Jobs in San Francisco, CA

public benchmark project.

…clear recommendations Validate models using benchmarking

Design and build benchmarks and evaluation methods that measure LLM capabilities in both text and multimodal modalities.

Build and maintain capability benchmarks like our Legal Agent Benchmark (LAB), along with product-focused evals that track how models perform on

Experience defining product KPIs, benchmarking methodologies, and launch readiness metrics for hardware products.

…experience building or maintaining evaluations, benchmarks, graders, or model-quality systems for large language or multimodal models.

…to ML research code or benchmarks.

…bay, not just on the benchmark

Benchmarks that stay meaningful.

…test harnesses and platform stress benchmarks, porting existing inference and training workloads to new, sometimes early-access

…and the applied sciences Create benchmarks

…for our post-training initiatives: the benchmarks, graders, and environments you build become the signal

…the return on ad spend benchmarks