Remote Frontier AI Data Scientist: Evaluation & Systems

Crossing Hurdles; United States; On-site; USD 600,000 - 2,000,000; Full time

Job summary

Crossing Hurdles is seeking a Senior Member of Technical Staff (Frontier AI) for a fully remote, full-time role. You will own end-to-end research and evaluation initiatives, shaping data systems and pipelines that drive model performance across diverse tasks.

You will analyze failures, define robust evaluation frames, and collaborate with cross-functional teams to communicate progress with evidence. The role emphasizes discretion, ownership, and clear written and verbal communication to

Qualifications

• Strong judgment on when research work is ready to be externalized.
• Experience designing machine learning-oriented datasets and evaluation frameworks.
• Ability to translate messy real-world behavior into structured research opportunities.

Responsibilities

• Own end-to-end research and evaluation initiatives, including problem framing, data design, quality calibration, and signal validation.
• Design ML-oriented data systems, task definitions, annotation schemas, rubrics, incentives, and pipelines for downstream model performance.
• Analyze model and system failures to identify root causes, edge cases, and improvement opportunities.
• Translate ambiguous real-world behavior into structured evaluation frameworks and new data categories.
• Iterate rapidly on evaluations, datasets, and feedback loops to improve system performance.
• Partner with cross-functional teams to translate research progress into credible narratives grounded in evidence.

Skills

Research signal quality

ML data design

Evaluation frameworks

Quality assurance processes

Stakeholder communication

Job description

Crossing Hurdles is seeking a Senior Member of Technical Staff (Frontier AI) for a fully remote, full-time role. You will own end-to-end research and evaluation initiatives, shaping data systems and pipelines that drive model performance across diverse tasks.

You will analyze failures, define robust evaluation frames, and collaborate with cross-functional teams to communicate progress with evidence. The role emphasizes discretion, ownership, and clear written and verbal communication to