Curated roles
Browse roles focused on reducing risks from advanced AI systems, including alignment research, safety engineering, evaluations and related operations.
364 active roles found.
Lead a research program on Provable AI Safety, focusing on building AI systems that verify their own correctness and collaborating with teams to advance AI safety.
The AI Security Systems Architect will design and develop systems for security testing and evaluation of AI technologies, focusing on adversarial testing methodologies and ensuring the resilience and security of AI systems.
Research scientist role focused on designing and running evaluations of AI harmful manipulation for EU AI Act enforcement, including frontier model evals, red-teaming, and regulator-facing reporting.
Technical project manager for a research division building harmful-manipulation evaluations for the EU AI Office, coordinating delivery, budgets, partners, and hiring for AI safety evaluation work.
The Research Scientist (Control) role focuses on AI safety by developing monitoring tools and protocols to reduce risks from AI systems, emphasizing empirical research and real-world applications.
Software engineer on AISI's Core Technology Team building evaluation frameworks, evaluation-at-scale systems, and model hosting infrastructure for frontier AI safety research.
The Research Engineer for Code RL will advance AI models' coding capabilities, ensuring safety and effectiveness through collaboration with alignment and red teams, focusing on responsible AI development.
Senior analyst role at OpenAI focused on assessing and mitigating agentic risks across products and platforms, using evaluations, red teaming, investigations, and cross-functional risk coordination.
Product manager for Anthropic’s Safeguards team, building safety systems, evals, and interventions to mitigate risks from frontier AI models and user misuse.
The role involves conducting research in AI safety and alignment, focusing on model evaluations and interpretability techniques, while collaborating with top researchers to address critical AI challenges.
People management and technical leadership role guiding ML research projects for LawZero’s AI safety agenda and safe-by-design AI systems.
The Digital Media Accelerator supports creators producing content that raises awareness about AI developments and issues, particularly regarding AI safety and risk.
Research engineer role focused on scalable interpretability assistants, evaluations for undesirable model behaviors, and AI oversight capabilities.
The Research Scientist role at Sequent focuses on AI alignment research, requiring contributions to both empirical and theoretical aspects of alignment problems.
Research engineer building infrastructure and automation for AI alignment research, including experiment orchestration, analysis pipelines, autoformalization tools, and evaluation infrastructure for frontier-tier models.
The role involves conducting research on AI safety and alignment, focusing on model evaluations and innovative alignment techniques.
Software engineer building evaluation infrastructure for Anthropic’s safety investigation and abuse detection systems, including datasets, metrics, and pipelines that assess misuse detection and robustness.
The Foresight Institute is offering grants for projects focused on AI safety, specifically in secure AI and neurotechnology for safe AI.
Analytics Engineer on OpenAI’s Safety Systems team building canonical datasets, dashboards, and data products for safety metrics and decision-making around safe, robust, reliable AI deployment.
Fellowship focused on adversarial red teaming and model evaluations for AI systems, identifying vulnerabilities, safety risks, and failure modes.