Research Scientist, AI Safety and Alignment

Sourced from careerholo.com

Scale Labs is hiring a Research Scientist to advance technical AI safety and alignment research on frontier models and agents. You will design control protocols, build alignment evaluations, and study monitorability and multi-agent risks, publishing findings and informing policymakers. The role bridges frontier AI research and policy through collaboration with industry, government, and academia.

• Design and stress-test control protocols and monitoring systems to detect and limit unsafe model and agent behavior
• Build alignment evaluations probing deception, sabotage, scheming, and reward hacking
• Study monitorability and whether model reasoning stays faithful and legible for supervision
• Investigate emergent risks in multi-agent systems such as collusion and coordination failures
• Develop threat models and evaluations for AI systems that automate AI R&D
• Collaborate with government agencies and labs to scope and design risk evaluations
• Publish research and write technical reports for policymakers

• Commitment to promoting safe, secure, and trustworthy AI
• Practical experience conducting technical research collaboratively
• Comfort building and instrumenting ML pipelines and evaluation harnesses
• Familiarity with current AI safety and alignment research
• Track record of published ML research, particularly in AI safety and alignment
• At least three years of experience on sophisticated ML problems in research or product development
• Strong written and verbal communication skills

• Experience designing evaluations and benchmarks or analyzing model/agent trajectories at scale
• Experience with red-teaming or adversarial testing of AI systems
• Familiarity with AI safety policy and governance frameworks (NIST AI RMF, EU AI Act, Korea AI Basic Act)