Impress employers and recruiters.
Choose from hundreds of resume examples.

Target Resume Now

Tailor your resume to this Control Red Team - Research Engineer/Research Scientist role.

Rezi rewrites your resume against AI Security Institute's job description. Free.

Resume score gauge reading 58 out of 100

Don't guess if your resume is good enough.

See how it scores against the Control Red Team - Research Engineer/Research Scientist posting at AI Security Institute — free, in seconds.

About the Role

The AI Security Institute is seeking individuals to join the Control Red Team to stress-test control monitors for advanced AI systems. This role involves researching and testing methods to detect and prevent misaligned behavior, contributing to the safety and governance of AI development globally.

Responsibilities

Design and run ML experiments, including RL and optimization-heavy work.
Build adversarial attacks to generate evidence for monitor efficacy.
Write and present research arguments.
Conduct evaluations of frontier labs' monitors.
Perform threat modeling of AI attacker operations.
Break monitors, sandboxes, and surrounding infrastructure.
Conduct security analyses.
Produce decision-relevant and action-guiding reports for companies and government.
Build tooling and experimental pipelines for rapid, reusable results.
Utilize LLMs to automate attack, evaluation, and analysis loops.
Build and run infrastructure for training and serving models at scale.

Requirements

Demonstrated ability to design, build, and run ML experiments on frontier models.
Ability to work autonomously on complex research projects with substantial engineering.
Experience with black-box work (API-based evaluations and attacks).
Experience with white-box work (e.g., fine-tuning open-weight models).
Strong software engineering and ML experience.
Ability to write clean, documented, reusable code for ML experiments.
Experience with LLM finetuning and inference frameworks, or evaluation frameworks like Inspect.
Ability to understand and critique how experiments support safety claims.
Understanding of why AI safety and control are hard problems, or a strong desire to learn quickly.
Impact-driven mindset.
Collaborative team player.
Flexibility in task execution.
High velocity and quality bar for outputs.

Skills

Machine Learning Experiments
Reinforcement Learning
Optimization
Adversarial Attacks
ML Experiment Design
LLM Finetuning
LLM Inference
Evaluation Frameworks (e.g., Inspect)
AI Safety
AI Control
Software Engineering
Threat Modeling
Security Analysis
Tooling and Pipeline Development
ML Infrastructure
Cybersecurity
LLM Coding Tools
Agent-based Systems

Location

London
Birmingham
Cardiff
Darlington
Edinburgh
Salford
Bristol

Work Type

Hybrid working
Occasional remote work abroad

Experience Level

Open on seniority
Experience leading research teams (for expanded scope)

Salary/Compensations

£65,000–£145,000 (base salary plus technical allowance)
Level 3: £65,000–£75,000
Level 4: £85,000–£95,000
Level 5: £105,000–£115,000
Level 6: £125,000–£135,000
Level 7: £145,000

Benefits

Direct influence on frontier AI governance and deployment
Work with Prime Minister’s AI Advisor and leading AI companies
Shape the first & best-resourced public-interest AI security research team
Pre-release access to multiple frontier models
Ample compute resources
Extensive operational support
Work with experts across national security, policy, AI research, and adjacent sciences
Ownership of important problems early
5 days off for learning and development
Annual stipends for learning and development
Funding for conferences and external collaborations
Freedom to pursue research bets without product pressure
Opportunities to publish and collaborate externally
Modern central London office
Option to work in similar government offices in Birmingham, Cardiff, Darlington, Edinburgh, Salford or Bristol
Flexibility for occasional remote work abroad
Stipends for work-from-home equipment
At least 25 days’ annual leave
8 public holidays
Extra team-wide breaks
3 days off for volunteering
Generous paid parental leave (36 weeks UK statutory leave shared + 3 extra paid weeks + option for additional unpaid time)
28.97% employer pension contribution on base salary
Discounts for cycling to work, donations, and retail/gyms

About the Company

The AI Security Institute is the world's largest and best-funded team dedicated to understanding advanced AI risks and translating that knowledge into action.
Located within the UK government with direct lines to No. 10.
Works with frontier developers and governments globally.
Uniquely positioned to mobilize governments for advanced AI safety.
Possesses resources, agility, and international influence to shape AI development and government action.
The Control Red Team is part of a group of about a dozen people focused on breaking developer alignment and misuse safeguards.
Grew out of AISI's previous research into control evaluations and safety cases.

Equal Opportunity

The Civil Service embraces diversity and promotes equal opportunities.
Runs a Disability Confident Scheme (DCS) for candidates with disabilities who meet the minimum selection criteria.
Offers a Redeployment Interview Scheme to civil servants at risk of redundancy who meet the minimum requirements.
The Civil Service is committed to attract, retain and invest in talent wherever it is found.
As part of the application process, statistics on D&I are monitored.