CrawlJobs Logo

Threat & Adversarial AI Expert

https://www.randstad.com Logo

Randstad

Location Icon

Location:
United Kingdom , City of London

Category Icon
Category:
IT - Software Development

Job Type Icon

Contract Type:
Employment contract

Salary Icon

Salary:

500.00 - 600.00 GBP / Day
Save Job
Save Icon
Apply Position

Job Description:

A pioneering financial institution is seeking an experienced Threat & Adversarial AI Expert to join their cybersecurity team. You will act as the primary architect of safety for the firm's generative AI ecosystem, ensuring agentic capabilities remain resilient against an evolving global threat landscape. As a Threat AI Expert, you will lead the organisation's Generative AI security strategy.

Job Responsibility:

  • Advanced Threat Modelling: Leading structured sessions using STRIDE and OWASP LLM/Agentic frameworks to map out attack trees for complex, non-deterministic systems
  • Adversarial Engineering: Translating emerging threats-such as Prompt Injection, Sleeper Agents, and Denial-of-Wallet-into rigorous test cases
  • AWS Bedrock Mastery: Overseeing the secure model lifecycle, including the configuration of Guardrails, Knowledge Bases (RAG), and Agentic tool-use
  • Regulatory Stewardship: Mapping the firm's safeguard catalogue against the specific demands of DORA, FCA Operational Resilience, and the EU AI Act
  • Collaborative Resilience: Running scenario-based workshops to validate control effectiveness, ensuring innovation never outpaces the firm's risk appetite

Requirements:

  • Proven track record in UK Financial Services with deep knowledge of FCA compliance and DORA
  • Solid grasp of Foundation Models (FMs), RAG, and the risks of non-deterministic agentic behavior
  • Mastery of OWASP LLM Top 10 and the NIST AI Risk Management Framework
  • Hands-on experience securing AWS Bedrock and governing the full AI model lifecycle
  • Ability to translate 'AI Red Teaming' outcomes into high-impact insights for both engineers and executives

Additional Information:

Job Posted:
May 17, 2026

Expiration:
June 10, 2026

Employment Type:
Fulltime
Work Type:
Hybrid work
Icon
Randstad - All Job Offers
Job Link Share:
Copy Link Icon
Facebook Icon Twitter Icon LinkedIn Icon

Looking for more opportunities? Search for other job offers that match your skills and interests.

Briefcase Icon

Similar Jobs for Threat & Adversarial AI Expert

Distinguished Engineer – AI Security

We're building a world of health around every individual — shaping a more connec...
Location
Location
United States , Scottsdale
Salary
Salary:
175100.00 - 334750.00 USD / Year
https://www.cvshealth.com/ Logo
CVS Health
Expiration Date
June 30, 2026
Flip Icon
Requirements
Requirements
  • 15+ years of AI experience, including significant depth in advanced technical or architectural roles
  • 5+ years of cybersecurity experience defining and integrating security standards and controls that aligned to established frameworks such as NIST CSF
  • Deep expertise in AI security concepts such as adversarial ML, secure model deployment, AI agent authorization, AI data loss protection, AI safety, and AI risk management
  • Strong background in Zero Trust architecture and hybrid infrastructure security
  • Demonstrated ability to lead and influence large-scale, cross-functional security initiatives
  • Hands-on experience building, deploying, and securing AI systems and platforms in enterprise environments
  • Practical experience applying AI security and risk management frameworks in real-world engineering contexts
  • AI Security Frameworks: MITRE ATLAS, NIST RMF, ISACA AI Audit Toolkit, and emerging ISO/IEC AI security standards
  • AI Technologies: Expert conceptual and hands-on implementation knowledge of core ML and generative AI technologies including transformer-based NLP, LLM-based generative AI and agentic AI
  • AI Risk Management & Model Security: Threat modeling, adversarial defenses, model lifecycle security, and vulnerability management
Job Responsibility
Job Responsibility
  • Define and help execute the enterprise AI security strategy, spanning secure model selection, development, and deployment criteria, adversarial threat mitigation, and alignment with emerging AI governance requirements
  • Design, build, and maintain reusable AI security frameworks, reference patterns, and technical standards for model integrity, secure data pipelines, and privacy-preserving machine learning
  • Perform hands-on security assessments of AI systems, identify risks, and provide mitigation guidance based on AI security posture management and detection findings
  • Drive innovation in AI security techniques, controls, and tooling through applied research and practical implementation
  • Apply and guide the application of AI security frameworks such as MITRE ATLAS, NIST RMF, and emerging ISO/IEC AI standards to secure the end-to-end AI lifecycle
  • Apply Zero Trust principles to hybrid and cloud infrastructure environments supporting AI workloads, including workload identity, segmentation, and continuous verification
  • Partner closely with Enterprise Architecture and Platform Engineering to integrate AI security controls into infrastructure design patterns and shared services
  • Guide and, where appropriate, directly implement security capabilities across on-premises and cloud platforms to ensure consistent protection for AI and traditional systems
  • Hands-on Engineering & Prototyping: Design and build proof-of-concept solutions, reference implementations, and reusable components to validate AI security and infrastructure security approaches
  • Framework and Pattern Development: Architect repeatable security patterns and guardrails that can be adopted by data science, engineering, and platform teams
What we offer
What we offer
  • Affordable medical plan options
  • 401(k) plan (including matching company contributions)
  • Employee stock purchase plan
  • No-cost programs for all colleagues including wellness screenings, tobacco cessation and weight management programs, confidential counseling and financial coaching
  • Paid time off
  • Flexible work schedules
  • Family leave
  • Dependent care resources
  • Colleague assistance programs
  • Tuition assistance
  • Fulltime
Read More
Arrow Right

Security Architect

The Security Architect role focuses on designing secure architectures for cloud ...
Location
Location
United Kingdom , Birmingham
Salary
Salary:
Not provided
nttdata.com Logo
NTT DATA
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Security-first mindset
  • 5+ year’s experience in information security, cloud security and architecture roles
  • Strong knowledge of security governance, risk and compliance frameworks (ISO 27001, NIST CSF/800‑53, NIS2, DORA)
  • Strong communication skills and ability to work with senior stakeholders
  • Experience mentoring teams or influencing security decisions
  • Google Cloud Platform (GCP) cloud‑native architecture design
  • Deep hands‑on experience with GCP security services and GCP security best practices
  • Experience architecting secure multi‑project setups and identity boundaries
  • Experience designing security for agent‑based AI systems and LLM‑integrated applications
  • Hands‑on experience with AI/LLM security controls (prompt security, model governance, secure APIs, orchestration security)
Job Responsibility
Job Responsibility
  • Translate business, data protection and security requirements into practical architectural designs leveraging industry frameworks (NIST, ISO 27001, CIS)
  • Design and maintain cloud‑native security architectures, with deep expertise in GCP architecture, security services, and secure workload design
  • Establish secure architectural patterns and standards across cloud platforms, with specific focus on GCP IAM, VPC Service Controls, Cloud Armor, Confidential Computing, and secure workload segmentation
  • Develop security design documentation, diagrams, and rationale aligned with business and compliance requirements
  • Apply risk‑based and threat‑based approaches to recommend secure and proportionate solutions
  • Designing security architectures for agent‑based AI systems, including orchestration frameworks, tool‑use agents, and multi‑agent workflows
  • Implementing AI/LLM security controls across: Model security (input/output filtering, model guardrails), Prompt security, adversarial prompt defense, prompt isolation, API & orchestration security, including secure agent tool use, Data security for vector stores, embeddings, and retrieval services
  • Performing AI‑specific threat modelling, including: Model extraction & poisoning, Hallucination‑driven risk, Sensitive data leakage, Toxic output & jailbreak attempts
  • Advising on secure integration of AI with cloud environments, focusing on compliant, privacy‑aware design
  • Conduct comprehensive risk assessments and threat modelling for cloud and AI systems
What we offer
What we offer
  • We offer a range of tailored benefits that support your physical, emotional, and financial wellbeing
  • Our Learning and Development team ensure that there are continuous growth and development opportunities for our people
  • We also offer the opportunity to have flexible work options.
Read More
Arrow Right

Security Architect – GCP & Agentic AI

The Security Architect role focuses on designing secure architectures for Google...
Location
Location
United Kingdom , London
Salary
Salary:
Not provided
nttdata.com Logo
NTT DATA
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • 5+ year’s experience in information security, cloud security and architecture roles
  • Strong knowledge of security governance, risk and compliance frameworks (ISO 27001, NIST CSF/800‑53, NIS2, DORA)
  • Strong communication skills and ability to work with senior stakeholders
  • Experience mentoring teams or influencing security decisions
  • Google Cloud Platform (GCP) Cloud‑native architecture design (GCP‑focused)
  • Deep hands‑on experience with GCP security services and GCP security best practices
  • Experience architecting secure multi‑project setups and identity boundaries
  • Agentic AI Security Experience designing security for agent‑based AI systems and LLM‑integrated applications
  • Hands‑on experience with AI/LLM security controls (prompt security, model governance, secure APIs, orchestration security)
  • AI‑specific threat modelling expertise
Job Responsibility
Job Responsibility
  • Translate business, data protection and security requirements into practical architectural designs leveraging industry frameworks (NIST, ISO 27001, CIS)
  • Design and maintain cloud‑native security architectures, with deep expertise in GCP architecture, security services, and secure workload design
  • Establish secure architectural patterns and standards across cloud platforms, with specific focus on GCP IAM, VPC Service Controls, Cloud Armor, Confidential Computing, and secure workload segmentation
  • Develop security design documentation, diagrams, and rationale aligned with business and compliance requirements
  • Apply risk‑based and threat‑based approaches to recommend secure and proportionate solutions
  • Designing security architectures for agent‑based AI systems, including orchestration frameworks, tool‑use agents, and multi‑agent workflows
  • Implementing AI/LLM security controls across: Model security (input/output filtering, model guardrails), Prompt security, adversarial prompt defense, prompt isolation, API & orchestration security, including secure agent tool use, Data security for vector stores, embeddings, and retrieval services
  • Performing AI‑specific threat modelling, including: Model extraction & poisoning, Hallucination‑driven risk, Sensitive data leakage, Toxic output & jailbreak attempts
  • Advising on secure integration of AI with cloud environments, focusing on compliant, privacy‑aware design
  • Conduct comprehensive risk assessments and threat modelling for cloud and AI systems
What we offer
What we offer
  • We offer a range of tailored benefits that support your physical, emotional, and financial wellbeing
  • Our Learning and Development team ensure that there are continuous growth and development opportunities for our people
  • We also offer the opportunity to have flexible work options
Read More
Arrow Right

AI Security Engineer

Perplexity is seeking a highly skilled, experienced, and hands-on AI Security En...
Location
Location
United States , San Francisco
Salary
Salary:
210000.00 - 385000.00 USD / Year
perplexity.ai Logo
Perplexity
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Hands-on coding and prompting experience
  • Bachelor of Science or Master of Science in Computer Science or a related field, or equivalent experience
  • Be a technical and process subject matter expert regarding AI security services and attacker tactics, techniques, and procedures
  • Good understanding of LLMs, AI architecture patterns, machine learning models, and related technologies such as MCP
  • Understanding of application security principles and secure coding practices
  • Experience developing and implementing security procedures and policies
  • Strong problem-solving, project management, leadership, and communication skills
  • Self-motivated with a willingness to take ownership of tasks
  • 4+ years of industry experience
Job Responsibility
Job Responsibility
  • Define, build, and refine mechanisms to secure AI systems (including self-hosted models, LLM APIs, agents, MCPs, and other core components of the AI stack) against adversarial behavior of all kinds
  • Understand technically complex AI systems, identify potential weaknesses in their architecture, and implement improvements
  • At least 50% of time performing hands-on remediation. Also working closely with peer engineers to drive remediations
  • Plan and carry out threat modeling activities and realistic threat simulations across our offerings
  • Conduct cybersecurity evaluations and lead AI security assessments in a cross-functional environment
  • Develop initiatives that improve our capabilities to effectively evaluate AI systems and enhance the organization's prevention, detection, response, and threat hunting capabilities
  • Provide guidance and education to developers to help deter and prevent threats
What we offer
What we offer
  • Equity
  • Health
  • Dental
  • Vision
  • Retirement
  • Fitness
  • Commuter and dependent care accounts
  • Fulltime
Read More
Arrow Right
New

AI Security Services Lead

Join Barclays as an AI Security Services Lead - Barclays is seeking an AI Securi...
Location
Location
United Kingdom , Knutsford; London
Salary
Salary:
Not provided
barclays.co.uk Logo
Barclays
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Security Engineering & Operations Expertise -Deep experience in designing, operating, and scaling enterprise security controls, with strong operational ownership and seamless integration into SOC, IAM, cloud, and CI/CD environments
  • AI/ML Systems & Threat Understanding- Strong understanding of AI/ML platforms (including data pipelines, model training, inference, and model repositories) and AI‑specific threats such as model poisoning, data leakage, adversarial inputs, and misuse of generative outputs
  • Enterprise Integration & Cross‑Functional Leadership -Proven ability to embed AI security controls into enterprise platforms and workflows through close collaboration with CTO, platform engineering, and wider CISO teams
  • Specialist AI Security Subject Matter Depth - Hands‑on experience with AI/ML security techniques, tools, or frameworks, such as adversarial ML, model scanning, AI guardrails, MITRE ATLAS, and secure AI lifecycle approaches
  • AI Governance, Standards & Regulatory Knowledge - Familiarity with AI security and governance frameworks including NIST AI RMF, ISO/IEC 42001, and emerging regulations such as the EU AI Act, with experience translating these into practical technical controls
  • Strategic Planning, Budgeting & Vendor Management -Experience shaping multi‑year security capability roadmaps, building investment cases, and managing specialist vendors delivering AI security tooling and services
Job Responsibility
Job Responsibility
  • Collaboration with stakeholders to understand their security requirements in business processes and IT projects, to enhance overall risk management
  • Execution of risk assessments to identify and prioritise potential cybersecurity threats that could impact the banks operations and data and guide the implementation of mitigation strategies and communicate findings to relevant findings to relevant senior stakeholders
  • Collaboration with business units to develop and implement security policies and procedures for the banks operations aligned to the risk management framework
  • Management of the implementation, testing and monitoring of security controls across the banks IT systems to ensure the effectiveness of controls and mitigation of risk
  • Execution of training content and sessions to educate employees, enhance cybersecurity awareness and provide guidance on safe online practices
  • Management of complex cybersecurity incidents by collaborating with IT teams and response experts to effectively resolve cases through analysis, expertise support and project supervision
  • Identification of emerging cybersecurity trends, threats, and new technologies to address potential risks by advocating the adoption of new security solutions
What we offer
What we offer
  • Competitive holiday allowance
  • Life assurance
  • Private medical care
  • Pension contribution
  • Fulltime
Read More
Arrow Right

Principal Security Research Manager

Microsoft Defender Experts provides expert-led services that help organizations ...
Location
Location
India , Hyderabad
Salary
Salary:
Not provided
https://www.microsoft.com/ Logo
Microsoft Corporation
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • 15+ years of experience which should include experience in managing direct teams and leading Security research and operations in a large environment
  • Good understanding of large-scale enterprise IT infrastructure, including cloud and hybrid setup
  • Deep knowledge of various kinds of attacks, threats and mitigation measures
  • Ability to communicate effectively across a globally distributed team
  • Computer science or related educational degree
  • Proven experience around scaling security operations using technology and automation
Job Responsibility
Job Responsibility
  • Run managed detection and response operations, in close partnership with a globally distributed team
  • Lead our coordinated response to complex security threats and incidents to effectively protect our global customers
  • Use advanced tools, real-time analytics, AI and threat intelligence to rapidly detect an adversary and evict them from our customer’s environment
  • Collaborate with engineering, program management and researchers across defender products to help enhance Defender Experts capabilities
  • Manage scale of research, operations through automation and innovation and driving operational excellence through a data-driven approach
  • Attract, coach and retain the best talent in the industry
  • Fulltime
Read More
Arrow Right

Principal AI Security and Safety Researcher

Security represents the most critical priorities for our customers in a world aw...
Location
Location
United States , Redmond
Salary
Salary:
139900.00 - 274800.00 USD / Year
https://www.microsoft.com/ Logo
Microsoft Corporation
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • Doctorate in Statistics, Mathematics, Computer Science, Computer Security, or related field AND 3+ years experience in software development lifecycle, large-scale computing, threat analysis or modeling, cybersecurity, vulnerability research, and/or anomaly detection
  • OR Master's Degree in Statistics, Mathematics, Computer Science, Computer Security, or related field AND 4+ years experience in software development lifecycle, large-scale computing, threat analysis or modeling, cybersecurity, vulnerability research, and/or anomaly detection
  • OR Bachelor's Degree in Statistics, Mathematics, Computer Science, Computer Security, or related field AND 6+ years experience in software development lifecycle, large-scale computing, threat analysis or modeling, cybersecurity, vulnerability research, and/or anomaly detection
  • OR equivalent experience
  • Ability to meet Microsoft, customer and/or government security screening requirements are required for this role
  • This position will be required to pass the Microsoft background and Microsoft Cloud background check upon hire/transfer and every two years thereafter
Job Responsibility
Job Responsibility
  • Lead cross-domain frontier harms strategy, represent as industry frontier forums, and coach individual operator leads on specific harm areas
  • Discover and exploit GenAI vulnerabilities end-to-end in order to assess the safety of systems
  • Manage product group stakeholders as priority recipients and collaborators for operational sprints
  • Drive clarity on communication and reporting for red teaming peers when working with product groups
  • Work alongside traditional offensive security engineers, adversarial ML experts, developers to land responsible AI operations while creating a culture of positive, inclusive problem solving
  • Fulltime
Read More
Arrow Right

Senior Security Researcher

Security is one of the most critical priorities for our customers in a world cha...
Location
Location
India , Bangalore
Salary
Salary:
Not provided
https://www.microsoft.com/ Logo
Microsoft Corporation
Expiration Date
Until further notice
Flip Icon
Requirements
Requirements
  • 7+ years of experience in cybersecurity, with strong hands-on understanding of the modern attacker kill chain, MITRE ATT&CK framework, and evolving identity-based threats, including attacks targeting SaaS applications, OAuth-based Enterprise Apps, and emerging AI-driven applications
  • Bachelor’s degree in Computer Science, Engineering, Information Technology, or a related technical discipline, or equivalent practical experience in security research or threat detection
  • Deep knowledge of adversary tooling, red team frameworks, and attacker techniques, with the ability to analyze, simulate, and interpret real-world attacker behaviors across identity and cloud ecosystems
  • Proficiency in at least one programming language (e.g., Python, C, or C++) for building research prototypes, internal tools, automation, or detection logic
  • Strong proficiency in query languages such as KQL, SQL, or Cypher for large-scale telemetry analysis, threat hunting, behavioral investigations, and detection validation
  • Experience working with large-scale datasets to support detection development, proactive threat hunting, behavioral analytics, and signal quality improvement
  • Strong collaboration and communication skills, with the ability to clearly articulate research insights, influence product and engineering decisions, and work effectively with partner teams, including Engineering, Data Science, and incident response stakeholders
Job Responsibility
Job Responsibility
  • Research attacker tradecraft and evolving threat patterns across cloud identity ecosystems, including OAuth, Enterprise Applications, third‑party SaaS platforms (e.g., Okta), emerging AI applications, and end‑to‑end authentication flows, with a strong focus on real‑world identity abuse techniques
  • Conduct proactive threat hunting across Microsoft Defender and Entra product signals to uncover identity‑based attacks, abuse paths, and misconfigurations
  • Design and deliver high‑quality detections, analytics, and risk insights by correlating multi‑product telemetry with attacker context
  • Partner with Engineering and PM teams to translate research findings into scalable, customer‑facing protection capabilities
  • Collaborate with Data Science teams to develop ML/AI‑based anomaly detection models, risk scoring frameworks, and hunting algorithms
  • Publish and communicate research outcomes through internal papers, external blogs, and conference presentations, representing Microsoft’s thought leadership in identity threat detection and cloud application security
  • Act as a Subject Matter Expert (SME) for identity threats by supporting customer incidents, field engagements, and internal incident response teams with deep context on attacker techniques, abuse patterns, and emerging trends
  • Work cross‑functionally with red teams, blue teams, infrastructure teams, and product groups to validate attack paths, simulate real‑world abuse scenarios, and continuously improve defensive coverage
  • Maintain strong research hygiene, including dataset curation, methodology documentation, signal quality assessment, and continuous improvement of detection efficacy
  • Fulltime
Read More
Arrow Right