Research Engineer / Scientist, Alignment Science – London
Anthropic
Research Engineer / Scientist, Alignment Science – London Overview
| Company Name | Anthropic |
| Job Role | Research Engineer / Scientist, Alignment Science – London |
| Qualifications | Bachelor’s |
| Category | IT Jobs |
| Job Type | Full Time |
| Location | London |
Anthropic is on a mission to develop reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society. We are expanding our team of dedicated researchers, engineers, policy experts, and business leaders to build these beneficial AI systems.
As a Research Engineer in Alignment Science, you will play a crucial role in designing and executing sophisticated machine learning experiments aimed at understanding and guiding the behavior of powerful AI systems. Your work will focus on ensuring AI is helpful, honest, and harmless, particularly in the context of human-level capabilities.
Key Responsibilities:
- Design and conduct comprehensive machine learning experiments to analyze and guide the behavior of advanced AI systems.
- Engage in exploratory research focused on AI safety, particularly concerning risks associated with future powerful systems.
- Collaborate with various teams, including Interpretability, Fine-Tuning, and the Frontier Red Team, to enhance research outcomes.
- Develop methods to ensure that advanced AI systems remain safe and effective in unpredictable or adversarial situations.
- Create model organisms to better understand potential alignment failures and improve empirical insights.
- Run experiments that contribute to key AI safety initiatives, including the implementation of the Responsible Scaling Policy.
- Write scripts and prompts to generate evaluation questions aimed at testing models’ reasoning abilities in safety-critical contexts.
- Contribute to research papers, blog posts, and presentations by providing ideas, figures, and writing.
Qualifications:
- Possess substantial experience in software development, machine learning, or research engineering.
- Have a background in empirical AI research projects.
- Demonstrate familiarity with technical AI safety research.
- Prefer collaborative, fast-paced projects over extensive independent work.
- Be willing to take on additional responsibilities beyond the job description.
- Show a strong interest in the societal impacts of AI.
Benefits:
- Competitive salary ranging from £260,000 to £370,000 GBP annually.
- Flexible working hours and a hybrid work policy requiring at least 25% time in the office.
- Generous vacation and parental leave policies.
- Optional equity donation matching program.
- A collaborative and supportive office environment.
We encourage candidates from all backgrounds to apply, even if they do not meet every single qualification. We believe that diverse perspectives are essential in AI development, and we strive to create an inclusive team.
For candidates requiring visa sponsorship, we do sponsor visas, but not all roles and candidates may qualify. If an offer is made, we will make every reasonable effort to assist with visa acquisition.
Join us at Anthropic and contribute to the future of AI safety!
Degree Requirement: Bachelor’s
Visa Sponsorship May be
To apply for this job please visit job-boards.greenhouse.io.