Longitude Labs - Member of the Technical Staff
Core
Design and own benchmarks, evals, and dataset taxonomies to set standards for AI data quality; conduct independent research and publish to establish thought leadership in AI benchmarks.
Role type
Senior IC research engineer (AI benchmarks & evaluation)
Builds
Benchmarks, evaluation frameworks, and high-quality datasets for frontier AI models
Domain
Artificial Intelligence / Machine Learning / Data Infrastructure
Deliverable
production ML models
Required skills
LLM benchmark design, eval methodology, data quality expertise, independent research, dataset construction
Preferred skills
PhD in ML/CS/CV or quantitative science, top-venue publications (ICML, NeurIPS), deep LLM expertise
Technologies
Python, PyTorch, LLMs, Evaluation Frameworks, Data Pipelines
Responsibilities
Design and own benchmarks, evals, and dataset taxonomies; Identify where frontier models fail and build datasets to close gaps; Partner with domain experts on high-quality data requirements; Drive the research agenda with autonomy
Seniority
Senior, hands-on IC