Curated roles
Browse roles focused on reducing risks from advanced AI systems, including alignment research, safety engineering, evaluations and related operations.
343 active roles found.
Role building evaluation task pipelines and infrastructure for frontier model testing, including systems to prevent models from detecting evaluations.
A remote global technical AI safety course covering alignment, RLHF, mechanistic interpretability, evaluations, and AI control, designed to prepare participants for AI safety careers.
The Chief Data Scientist will lead AI Safety research and development programs, focusing on national security missions, ensuring technical excellence and alignment with evolving mission requirements.
The AI Security & Control Engineer role focuses on designing threat models and control protocols against AI adversaries, improving the security of AI systems, and conducting red-teaming activities to enhance product safety.
Product engineer building interfaces, APIs, and workflows that operationalize interpretability research for training, evaluating, debugging, and deploying AI systems; relevant because it supports safety-related understanding of model internals and safer AI systems.
Technical programme manager for AISI’s Chem-Bio team, coordinating research programmes that evaluate frontier and narrow AI models in chemistry and biology for advanced AI risk assessment and policy-relevant evidence.
The role involves mitigating AI threats through monitoring, predicting misalignment, and establishing safeguards for future AI systems.
The Biosafety Red Teaming Specialist will lead efforts to identify and mitigate biological and chemical risks associated with AI systems, focusing on red teaming and misuse prevention.
Funding call for research on AI safety in multi-agent systems, including testbeds, agent networks, infrastructure, and oversight/control for frontier-model agents.
PhD/visiting PhD research role focused on AI safety, security, and alignment for advanced autonomous systems, including interpretability, evaluations, situational awareness, and red-teaming.
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 role involves identifying and analyzing AI/ML security vulnerabilities, participating in threat modeling for AI systems, and evaluating AI model robustness through security tests.
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.
In-person AI safety bootcamp focused on technical AI safety topics including interpretability, alignment strategies, technical governance, and AI risk discussions.
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.