[Expression of Interest] Research Engineer / Scientist, Alignment – London

Responsibilities

We are representing a confidential AI research organization seeking a Research Engineer/Scientist for their London-based alignment team. In this role, you will design and execute sophisticated machine learning experiments to understand and guide the behavior of advanced AI systems, with a particular focus on safety challenges in powerful future models.

Your work will involve:

• Testing the robustness of safety techniques by training language models to identify weaknesses in safety interventions
• Running multi-agent reinforcement learning experiments to evaluate novel safety approaches
• Building tooling to efficiently evaluate AI-generated safety challenges and jailbreak attempts
• Developing scripts and prompts to produce evaluation questions testing reasoning abilities in safety-critical contexts
• Contributing to research papers, blog posts, and technical presentations
• Supporting key safety initiatives including responsible scaling frameworks
• Collaborating with interpretability, fine-tuning, and red team specialists across the organization

Research areas of particular focus include AI control methods (ensuring advanced systems remain safe in unfamiliar scenarios) and alignment stress-testing (creating experimental frameworks to understand how alignment failures might emerge).

Note: This role requires at least 25% time in the London office and occasional travel to San Francisco, where the team's primary hub is located. All technical interviews are conducted in Python.

What We're Looking For

Required qualifications:

• Significant software engineering, machine learning, or research engineering experience
• Demonstrated contributions to empirical AI research projects
• Familiarity with technical AI safety research concepts
• Strong collaborative work style with preference for fast-moving team projects
• Willingness to contribute beyond strict role boundaries
• Bachelor's degree in a relevant field or equivalent combination of education and experience

Valuable additional experience:

• Authoring research papers in machine learning, NLP, or AI safety
• Hands-on work with large language models
• Reinforcement learning implementation
• Managing Kubernetes clusters and complex shared codebases

You need not have 100% of the listed skills or formal certifications. We encourage applications from candidates who bring strong foundational experience even if they don't match every qualification.

How We Work with You

When you apply through Get A Job.ai, our talent team will review your application and conduct an initial screening to understand your background and fit for this specialized role. If there's a strong match, we'll submit your profile to our client for consideration. Please do not attempt to contact the client organization directly, as all communication should flow through our recruiting process to ensure proper representation.

Our client does offer visa sponsorship and retains immigration counsel to support successful candidates, though sponsorship viability varies by individual circumstances.

Pay

This position is based in London with hybrid work expectations. Compensation details will be discussed during the interview process based on experience level and qualifications.

Get A Job.ai is an equal opportunity recruiter. We welcome applications from candidates of all backgrounds and encourage those from underrepresented groups in technology to apply.