Loading open roles
TD Newton
About the role
•
Proposed designation:
AI Security Engineer Associate Consultant
•
Role type:
Permanent
•
Reporting to: Associate Director
•
Geo to be supported:
KDN
•
Work timings:
Flexible
•
Demonstrate foundational knowledge of cybersecurity and artificial
intelligence, supporting secure design and deployment of AI systems under
guidance from senior team members.
•
Assist in implementing and maintaining AI security policies and standards,
including controls for prompt injection, topic safety, output guardrails,
and basic behavioral monitoring in agentic systems.
•
Support threat modeling and risk analysis activities for GenAI and
multi‑agent AI systems by identifying common threats, misuse patterns, and
security gaps.
•
Contribute to ensuring compliance with AI regulations and data protection
requirements (e.g., EU AI Act, NIST AI RMF, GDPR, CCPA) through
documentation and control validation.
•
Participate in investigation and analysis of AI‑related security
incidents, such as prompt injection, content violations, and goal
manipulation, under senior supervision.
•
Operate and help tune AI security tools for anomaly detection,
vulnerability identification, and behavior monitoring of AI workflows.
•
Apply programming and scripting skills (preferably Python) to support
automation of AI security checks, monitoring tasks, and governance
workflows.
•
Support team efforts to promote AI security best practices, stay current
with emerging threats, and share learnings through documentation or
internal sessions.
Educational qualifications
·
Minimum Bachelor's degree in Computer Science, Information Technology or
MCA.
·
Preferred certifications: AI-specific security certifications.
Work experience
·
3+ years of experience in Cybersecurity with at least 2 years focused on
technical GenAI security
·
Strong knowledge of cybersecurity principles, threat modeling, and risk
assessment.
·
Expertise in GenAI security, including adversarial attack mitigation,
guardrail tuning, topic / sentiment classifiers.
·
Familiarity with AI security frameworks (NIST AI RMF, OWASP LLM Red
Teaming Guide & Top 10).
·
Proficiency in Python for GenAI developments and Security automatization
(at least Streamlit, AutoGen & Semantic Kernel, smolagents)
·
Hands-on experience with AI security tools (garak, giskard, fuzzyai) as
well as manual AI security testing (automation experience with Python is a
huge plus)
Key behavioral attributes/requirements
·
Ability to assess and test AI systems to identify common security
weaknesses and misconfigurations, with guidance from senior practitioners.
·
Good communication skills to collaborate with cross‑functional teams and
explain technical findings to non‑technical stakeholders.
·
Awareness of or participation in AI security communities or initiatives
(e.g., OWASP, CSA, open forums), with willingness to contribute over time.
·
Proactive and curious mindset with an interest in identifying potential
issues early and seeking guidance on effective remediation approaches.
·
Strong passion for emerging AI technologies and AI security trends, with
continuous learning through research, labs, or real‑world use cases.
Interest in understanding core AI system components, including model
behavior, infrastructure, and basic hardware or vendor‑specific
optimizations.
•
Interview process: 3
•
Does the job role involve travelling: No
•
Does the busy season apply to this role?: No