Software Engineer Cyber and Autonomous Systems Team
UK government research organisation that evaluates advanced AI risks and develops and tests mitigations to inform governments.
About AI Security Institute
The AI Security Institute (AISI) is a research organisation within the UK Department for Science, Innovation and Technology. It conducts technical research, evaluates leading AI systems, develops risk mitigations, and shares evaluation infrastructure such as Inspect.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build infrastructure and analysis tooling for cyber and autonomy evaluations at scale. You will lead testing exercises, turn evaluation results into insights, deliver technical projects from design through maintenance, and write robust Python software with testing, documentation, and observability.
Requirements
- Deliver and maintain production-quality software
- Demonstrate deep Python expertise and familiarity with its ecosystem and tooling
- Design and evolve software systems or technical architecture
- Demonstrate a strong interest in AI safety
- Take ownership of ambiguous and technically difficult problems
- Communicate clearly and improve engineering standards through feedback and mentoring
- Undergo a criminal record check and obtain BPSS clearance
Responsibilities
- Build infrastructure for cyber and autonomy evaluations at scale
- Develop analysis tooling and LLM-as-a-judge workflows
- Identify research questions and lead evaluation testing exercises
- Analyse results and communicate findings and recommendations
- Own technical projects and shared components from design through maintenance
- Write scalable, robust, maintainable Python software with testing, documentation, and observability
- Deploy and validate cyber ranges on evaluation infrastructure
- Collect, validate, and organise evaluation data for publication
Benefits
- Pre-release access to multiple frontier models and ample compute
- Operational support
- Annual learning and development stipends
- Conference and external-collaboration funding
- Hybrid working and flexibility for occasional remote work abroad
- Work-from-home equipment stipend
- At least 25 days of annual leave
- 8 public holidays
- Extra team-wide breaks
- 3 volunteering days
- Paid parental leave
- Employer pension contribution of 28.97% of base salary
- Cycling, donation, retail, and gym discounts and benefits