Frontier AI Red Team Engineer

AI Security Institute

Greater London

Hybride

GBP 65 000 - 145 000

Plein temps

Il y a 3 jours
Soyez parmi les premiers à postuler

Obtenez une réponse de cet employeur

Votre CV et votre lettre de motivation, adaptés exactement à ce que l’employeur recherche.

Passez les filtres ATS

Avantages offerts par ce poste

Hybrid working
25 days annual leave
Learning & development stipend
Conference funding
Work-from-home equipment stipend

Résumé du poste

AI Security Institute, based in London, seeks Software Engineers to join the Red Team. You will contribute to scalable red-teaming of frontier AI models and build tools for researchers, with opportunities across junior to principal levels.

Candidates experienced in automation, security, and scalable infrastructure are welcome. Hybrid working in the UK with direct impact on global AI safety and governance, joining a team collaborating with researchers, industry partners, and government

Qualifications

  • Writing production quality code at fast pace.
  • Interest in automating work with agents while accounting for limitations.
  • Designing, shipping, and maintaining complex tech products.
  • Improving technical standards across a team through mentoring and feedback.
  • Strong written and verbal communication skills.

Responsabilités

  • Build and maintain systems for running red-teaming against frontier models at scale, such as automated jailbreaking pipelines, alignment auditor agents in Inspect Petri, and attacker agents for control red-teaming.
  • Design and implement systems for running large scale automated research and engineering with many agents on AISI’s research platform.
  • Extend our evaluation tooling, built on Inspect (AISI's open-source framework for evaluating AI), to new kinds of targets.
  • Develop novel solutions to performance, reliability, and security problems that arise from running thousands of agents in parallel.
  • Work with Core Technology to share infrastructure and avoid duplicating work.
  • Help run pre-release testing of frontier models, often to tight deadlines.

Description du poste

AI Security Institute, based in London, seeks Software Engineers to join the Red Team. You will contribute to scalable red-teaming of frontier AI models and build tools for researchers, with opportunities across junior to principal levels.

Candidates experienced in automation, security, and scalable infrastructure are welcome. Hybrid working in the UK with direct impact on global AI safety and governance, joining a team collaborating with researchers, industry partners, and government

Obtenez votre examen gratuit et confidentiel de votre CV.

ou faites glisser et déposez votre fichier ici.

Similar jobs

Postes similaires à comparer

Hybrid Frontier AI Red Team Engineer
Hybrid Frontier AI Red Team Engineer

AI Security Institute (AISI) • Greater London

Hybride
GBP 65 000 - 145 000
Hybrid working
Annual learning stipend
Conferences funding
+1
Frontier AI Red Team Engineer: Scale & Secure
Frontier AI Red Team Engineer: Scale & Secure

EngRadar • Greater London

Sur place
GBP 65 000 - 145 000
Frontier AI Security Engineer – Core Tech Team (Hybrid)
Frontier AI Security Engineer – Core Tech Team (Hybrid)

AI Security Institute (AISI) • Greater London

Hybride
GBP 65 000 - 145 000
Hybrid working
Frontier models access
Operational support
+1
AI Security Red Team Engineer
AI Security Red Team Engineer

Refractal Ltd • Greater London

Hybride
GBP 65 000 - 125 000
Salary range £65k–£125k
Competitive equity
Pension contribution
+2
Frontier AI Safety Standards Lead
Frontier AI Safety Standards Lead

AI Security Institute • City Of London

Sur place
GBP 90 000 - 130 000
Frontier AI Deployment Engineer — London (Hybrid)
Frontier AI Deployment Engineer — London (Hybrid)

OpenAI, Inc. • Greater London

Hybride
GBP 100 000 - 150 000
Relocation assistance
Frontier AI Engineer for Mission-Critical Systems
Frontier AI Engineer for Mission-Critical Systems

Capgemini • Manchester

Hybride
GBP 90 000 - 130 000
Learning for life
Hybrid working
Training & certifications
+1
Frontier AI Safety & Research Engineering Manager
Frontier AI Safety & Research Engineering Manager

Google LLC • Greater London

Hybride
GBP 150 000 - 210 000
Equity program
AI Security Director — Frontier AI Research & Policy
AI Security Director — Frontier AI Research & Policy

AI Security Institute • City Of London

Hybride
GBP 131 000 - 160 000
Mission-driven colleagues
Influence on AI governance
Work with AI Advisor to the PM
+3
Frontier AI Safety Engineer — Remote
Frontier AI Safety Engineer — Remote

Crossing Hurdles • Grande-Bretagne

À distance
GBP 60 000 - 80 000