Curated roles
Browse roles focused on reducing risks from advanced AI systems, including alignment research, safety engineering, evaluations and related operations.
363 active roles found.
Senior security engineer role on DeepMind's Agentic Red Team focused on adversarial testing of AI agents, prompt injection, exploit development, and automated red-teaming frameworks for model safety.
Research positions in NLP and AI with a strong emphasis on trustworthy and safe AI, including agent reliability, evaluation science, interpretability, red-teaming, and robustness.
Contract research engineer role focused on frontier AI safety evaluations, dangerous behavior elicitation, and safety report writing for loss-of-control and harmful manipulation risks.
Remote researcher role producing public reviews of AI benchmarks, evaluating methodologies and implications for AI capabilities; adjacent to AI safety via model evaluations and capability assessment.
Senior research management role supporting AI safety programmes, including scoping and reviewing research, mentoring researchers, and running red-teaming and proposal development sessions focused on reducing AI risk.
Research scientist role at a non-profit AI safety lab focused on theoretical and empirical work on LLM-based agents, loss-of-control risks, and safety mitigations.
Senior technical role building and securing frontier AI datacenter infrastructure, including threat modeling and red-teaming against nation-state adversaries.
Senior communications leader for an AI safety research organization, responsible for external messaging, media strategy, and translating frontier AI safety research into public-facing materials.
Senior technical role on Cohere’s Safety for Agents team focused on data generation, post-training algorithms, and evaluation methods to improve safety, trustworthiness, and security of LLMs and agentic models.
Research scientist role at Resolution focused on technical AI alignment research, including empirical and theoretical work on scalable oversight and related alignment problems.
Research Engineer role at an ASI alignment lab, building research automation and evaluation infrastructure to support alignment research and frontier-model experiments.
Senior research engineer role on Cohere’s Safety / Modelling Safety and Trust team building data tooling and pipelines for training and evaluation data to support safer, more reliable models.
Research role focused on evaluating frontier AI models on real-world tasks, building benchmarks and rubrics, and analyzing model performance; directly relevant to AI evaluations and safety-adjacent capability assessment.
Lead research on frontier AI risk modeling across cyber, CBRN, and loss of control, setting methodological standards that inform safety cases, evaluations, mitigations, and AI governance.
Senior research engineering role focused on building evaluation methods, benchmarks, datasets, and infrastructure for measuring frontier LLM capabilities; relevant because it directly concerns model evaluations for advanced AI systems.
Product management role bridging Cohere's safety research and North product, translating model evaluations and red-teaming findings into safety features, guardrails, and evaluation frameworks.
Senior research role focused on creating next-generation evaluation methods, benchmarks, and infrastructure to measure LLM progress and model capabilities.
Senior technical staff role on Cohere’s Safety for Agents team focused on data generation, post-training algorithms, and evaluation methods to improve safety and trustworthiness of LLMs and agents.
Part-time remote contractor role annotating, auditing, and red-teaming LLM outputs to improve model safety, policy alignment, and prevention of unsafe or adversarial outputs.
Research Scientist role in Google DeepMind's Frontier AI unit focused on multimodal safety research, AI alignment, behavior assessment, and steering evolving AI systems.