Building safer foundational models through automated alignment research.
Leading the 2026 research initiatives for safe, constitutional foundational models.
Developing the alignment protocols for high-agency autonomous Claude-4 systems.
Scaling Claude's constitutional training pipelines for the UK research hub.
Developing the 2026 iteration of Claude's constitutional training pipelines.
Hardening the constitutional AI layers against autonomous agent jailbreaking.
Defining the safety guardrails for the 2026 Claude 'Active' models.
Building the 2026 iteration of Claude's constitutional training pipelines.
Developing the alignment protocols for high-agency autonomous Claude systems.
[Industry: Research Services | Type: Full-time | Level: Entry level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. Ou
[Applicants: Over 200 applicants | Industry: Research Services | Type: Full-time | Level: Mid-Senior level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI…
[Applicants: Over 200 applicants | Industry: Research Services | Type: Full-time | Level: Mid-Senior level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for o
[Applicants: Over 200 applicants | Industry: Research Services | Type: Full-time | Level: Mid-Senior level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI…
[Applicants: Over 200 applicants | Industry: Research Services | Type: Full-time | Level: Mid-Senior level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for o
[Applicants: Over 200 applicants | Industry: Research Services | Type: Full-time | Level: Mid-Senior level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI…
[Applicants: Over 200 applicants | Industry: Research Services | Type: Full-time | Level: Mid-Senior level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for o
[Industry: Research Services | Type: Full-time | Level: Mid-Senior level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our…
[Industry: Research Services | Type: Full-time | Level: Mid-Senior level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whol
[Applicants: Over 200 applicants | Industry: Research Services | Type: Full-time | Level: Mid-Senior level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI…
[Applicants: Over 200 applicants | Industry: Research Services | Type: Full-time | Level: Mid-Senior level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for o
[Applicants: Over 200 applicants | Industry: Research Services | Type: Full-time | Level: Mid-Senior level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI…
[Applicants: Over 200 applicants | Industry: Research Services | Type: Full-time | Level: Mid-Senior level] About AnthropicAnthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for o
