Curated roles
Browse roles focused on reducing risks from advanced AI systems, including alignment research, safety engineering, evaluations and related operations.
393 active roles found.
An intensive, fully-funded ten-week AI safety research fellowship in Cambridge focused on technical AI safety, governance, interpretability, formal verification, model evaluations, and risk management frameworks.
Security research role focused on AI auditing methodologies, AI system vulnerabilities, and tools/frameworks for evaluating AI safety and security.
Lead enforcement operations to detect and mitigate misuse of Anthropic AI systems for cyberattacks, malware, and offensive exploitation, including managing a team and shaping enforcement strategy.
Frontier AI red teaming role focused on attacking cyber safeguards, designing attack strategies, and feeding results into safety/alignment evaluations and deployment decisions.
Part-time technical advisor role for AI safety research on fine-tuning and evaluations, advising on benchmark design, generalization testing, and validity of welfare/capability evals for open-weight models.
Technical security researcher role focused on red-teaming AI agent systems, securing agent sandboxes and access controls, and building monitoring and controls to reduce catastrophic risks from coding agents.
Research engineer role on DeepMind’s AGI Safety and Alignment Team, focused on alignment methods, adversarially robust control systems, interpretability, and frontier-model safety work.
Research scientist role leading Frontier Safety Framework governance research and risk modeling for frontier AI models, including safety evaluations, mitigation assessment, and external safety reporting.
A 3-month full-time research fellowship in applied mathematics for AI safety, centered on technical AI alignment research and producing a research proposal.
Research scientist role focused on monitoring deployed GenAI models for safety, alignment, misuse, and coordinated harms using automated evaluations, classifiers, and large-scale production data.
Research engineer role on DeepMind's AGI Safety and Alignment Team focused on alignment methods, adversarially robust AGI control systems, and interpretability for frontier models.
Staff research scientist role focused on AI safety for biology, including safety evaluations, misuse-resistant safeguards, and frontier safety policy development.
Engineering manager for FAR.AI’s red team, leading engineering systems for frontier AI red-teaming, safety evaluations, attacker simulation, and safeguard testing.
Senior Model Policy Manager role focused on creating and operationalizing policies, taxonomies, and evaluation criteria to keep frontier AI systems safe, especially for biological and chemical risk.
Founding grantmaker for the AI Model Safety program, funding independent evaluations, standards, and foundational safety research to improve frontier model safety.
Senior AI red team role on SEI's AI Security team focused on adversary emulation against AI-enabled systems, developing offensive techniques to improve defender preparedness and AI system security.
Two-year postdoctoral research role on mechanistic interpretability and AI reasoning within an ERC-funded project on explainable and robust automatic fact checking. Relevant as adjacent AI safety work because it studies model internals and reasoning behavior.
Research scientist role on DeepMind's GenAI Safety team focused on production monitoring, automated evaluations, and misuse detection for deployed AI models.
Senior Model Policy role at OpenAI focused on designing policies, taxonomies, and evaluation criteria to keep frontier models safe in biological and chemical dual-use scenarios.
AI security researcher role focused on LLM security capabilities, benchmarks, risk identification, and security frameworks for model iteration.