Technical Staff Member

Job Summary

To drive research initiatives in frontier AI systems, the full-time Member of Technical Staff will evaluate and improve model capabilities by designing benchmarks, developing high-quality datasets, and analyzing model behavior in a remote work environment.

Key responsibilities

• Own research and evaluation initiatives from task design to benchmark validation and performance analysis
• Design and validate capability evaluations and reinforcement learning environments for emerging model capabilities
• Collaborate with researchers and domain experts to develop datasets, evaluation rubrics, and methodologies for model assessment

Required qualifications

• Strong technical background in computer science, machine learning, AI, or a related field
• Hands-on experience designing ML evaluations, benchmark suites, and research datasets
• Proficiency in Python and experience building data pipelines or evaluation tools
• Understanding of LLMs, foundation models, and evaluation methodologies
• Strong analytical skills in model failure analysis and experimental design