Mid-Level Research Engineer, Benchmarks

Clera is seeking a Mid-Level Research Engineer to join our early-stage AI evaluation infrastructure startup. You will design and implement rigorous benchmarks for frontier AI agents, translating real-world workflows into measurable evaluations. This role is crucial for helping technical teams understand agent performance in practical settings and requires a strong foundation in AI evaluation and infrastructure development.

• Design and implement benchmarks for frontier AI agents
• Collaborate with subject-matter experts to define evaluation criteria
• Build scalable infrastructure for running AI models and agents
• Develop metrics and analyses for benchmark quality
• Validate benchmark results against real-world performance
• Proficiency in Python, Docker, and Linux environments