Software Engineer Core Technology
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 and maintain research-oriented software and infrastructure for AI evaluations. You may develop Inspect sandbox plugins, add support for open-weight models, design custom research infrastructure, collaborate with the open-source community, and debug evaluation issues.
Requirements
- Write production-quality code efficiently
- Demonstrate Python expertise and familiarity with its ecosystem and tooling
- Communicate effectively in writing and verbally
- Work effectively with others and solve challenging problems
Responsibilities
- Develop features for Inspect sandbox plugins that support agentic evaluations
- Implement support for open-weight models on the model-hosting platform
- Design custom infrastructure for research projects
- Collaborate with the open-source community on Inspect and its plugin ecosystem
- Debug Inspect issues during frontier-model evaluation testing
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