Research Scientist, Frontier Red Team (Emerging Risks)

Anthropic(1 day ago)

HybridFull TimeSenior$350,000 - $850,000Policy

About this role

Research Scientist on Anthropic’s Frontier Red Team focused on understanding and defending against emerging societal risks from advanced AI systems. The role involves building an independent research program to scope and evaluate risks, run experiments and evaluations, and translate findings into insights for product, safeguards, and policy. It emphasizes producing research artifacts, demos, and tools to communicate model capabilities and inform decision-making.

View Original Listing

Required Skills

Research
Experimentation
Red Teaming
Eval Design
Benchmarking
Data Analysis
Program Building
Communication
Stakeholder Management
Tooling

+1 more

Qualifications

Bachelor's Degree

About Anthropic

anthropic.com

Anthropic is an AI safety and research company focused on building reliable, interpretable, and steerable AI systems. It develops large language models (branded as Claude) and offers APIs and enterprise products that let organizations integrate conversational AI with safety-focused controls, moderation, and privacy features. The company prioritizes interpretability and alignment research, publishes technical work, and engages with policymakers to reduce risks from advanced AI. Customers choose Anthropic for its safety-first approach, controllability tools, and research-driven models.