Autonomous Systems Research Scientist (AI Safety)

White Circle; Greater London; Hybrid; GBP 112,141 - 186,902; Full time

Benefits offered by this job

Relocation package

Medical insurance (France)

All hardware and tools provided

Subscriptions for AI agents/IDEs

Team off-sites

Job summary

White Circle seeks a research scientist to build autonomous, large-scale environments that test LLM agents and study failure modes. You will run end-to-end experiments across single and multi-agent systems and contribute to safety models.

Ideal candidates have a track record in empirical AI research, strong software engineering, and advanced degrees in a quantitative field. Relocation option and comprehensive benefits are offered.

Qualifications

• Experience building end-to-end agent environments or research pipelines.
• Strong track record in empirical AI research and evaluation.
• PhD or MSc in a quantitative field is highly desirable.

Responsibilities

• Design adversarial environments for single and multi-agent systems.
• Run end-to-end experiments against external APIs and internal models.
• Identify concrete agent failure modes and surface them at scale.
• Translate findings into robust safety models and writeups.
• Collaborate with researchers to advance AI safety tooling.

Skills

Agent environments

Multi-agent experiments

AI safety

Empirical research

Python tooling

Education

MSc or PhD in ML/CS

Tools

Docker

Kubernetes

Linux

Job description

White Circle seeks a research scientist to build autonomous, large-scale environments that test LLM agents and study failure modes. You will run end-to-end experiments across single and multi-agent systems and contribute to safety models.

Ideal candidates have a track record in empirical AI research, strong software engineering, and advanced degrees in a quantitative field. Relocation option and comprehensive benefits are offered.