AI Safety & Red Team Lead — On-Site London

Alice (Formerly ActiveFence)

Greater London

On-site

GBP 180,000 - 210,000

Full time

7 hours ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Alice is seeking an experienced, technically fluent AI Safety & Red Teaming Lead to oversee end-to-end delivery for a high-stakes Generative AI safety engagement in London. You will lead a specialized multidisciplinary pod of Child Safety Researchers, reverse engineers, and adversarial jailbreakers—bridging deep domain intelligence with technical exploit and evaluation methodologies.

You will own program execution and present findings to client leadership.

Qualifications

  • Leadership & Delivery Experience: 7+ years in Trust & Safety, AI Red Teaming, Threat Intelligence, or Offensive Security, incl. 3+ years managing multidisciplinary technical teams.
  • End-to-End Program Ownership: Track record delivering complex client/enterprise engagements from inception to executive delivery under tight timelines.
  • Child Safety & Online Harms Literacy: Understanding of CSAE/CSAM, grooming dynamics, and adversarial evasion.
  • Technical & Adversarial Fluency: Deep knowledge of Generative AI architectures, LLM/multimodal vulnerabilities, jailbreaking, reverse engineering & automated evaluation tooling.
  • Executive Communication & Client Presence: Excellent English communication; experience presenting to senior external stakeholders.
  • Workplace & Security Compliance: Ability to work on-site 5 days/week in a secured London office.
  • Content Resilience: Psychological resilience to oversee high-severity child safety investigations.

Responsibilities

  • End-to-End Delivery & Program Management: Lead full delivery lifecycle from scoping to final reporting, ensuring milestones and safety benchmarks.
  • Multidisciplinary Team Leadership: Manage on-site team of SMEs, reverse engineers, and jailbreakers, balancing workloads.
  • Methodology Review & Technical Approval: Review and approve adversarial testing frameworks and automated evaluation pipelines.
  • Client Stakeholder Management & Executive Reporting: Lead technical briefings and align testing outputs with client policy.
  • Operational Security & Wellbeing Governance: Enforce secure environment and oversee team wellbeing and resilience.

Skills

Leadership
Program ownership
AI red teaming
Threat intelligence
Offensive security
Executive communication
English proficiency
Workplace security compliance
Content resilience
Team management

Job description

Alice is seeking an experienced, technically fluent AI Safety & Red Teaming Lead to oversee end-to-end delivery for a high-stakes Generative AI safety engagement in London. You will lead a specialized multidisciplinary pod of Child Safety Researchers, reverse engineers, and adversarial jailbreakers—bridging deep domain intelligence with technical exploit and evaluation methodologies.

You will own program execution and present findings to client leadership.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

AI Safety & Red Team Lead | On-Site London
AI Safety & Red Team Lead | On-Site London

Alice • Greater London

On-site
GBP 120,000 - 170,000
AI Safety & Red Teaming Lead
AI Safety & Red Teaming Lead

Alice (Formerly ActiveFence) • Greater London

On-site
GBP 180,000 - 210,000
GenAI Safety Researcher: Child Safety Threat Intel (London)
GenAI Safety Researcher: Child Safety Threat Intel (London)

Alice • Greater London

On-site
GBP 70,000 - 105,000
AI Safety & Red Teaming Lead
AI Safety & Red Teaming Lead

Alice • Greater London

On-site
GBP 120,000 - 170,000
Technical Project Manager
Technical Project Manager

Alice • United Kingdom

On-site
GBP 110,000 - 140,000
Generative AI Red Team Lead
Generative AI Red Team Lead

ActiveFence • England

On-site
GBP 60,000 - 80,000
AI Safety TPM – London, Risk & Red-Teaming
AI Safety TPM – London, Risk & Red-Teaming

Cubiq Recruitment • Greater London

On-site
GBP 90,000 - 130,000
AI Red Team Leader
AI Red Team Leader

ActiveFence • England

On-site
GBP 60,000 - 80,000
Senior AI Safety Research Scientist
Senior AI Safety Research Scientist

Aisafety • Greater London

On-site
GBP 90,000 - 135,000
Open-Model AI Safety Lead: Red Team & Validation | Equity
Open-Model AI Safety Lead: Red Team & Validation | Equity

Reflection AI • Greater London

On-site
GBP 100,000 - 180,000
Top-tier compensation
Comprehensive medical, dental, and vision insurance
Paid parental leave for all new parents
+2