Allied Resources Technical Consultants
AI Security Analyst (Allentown)
Allied Resources Technical Consultants, Allentown, Pennsylvania, United States, 18103
IT Security Analyst II
AI & Emerging Technology Security (Contract)
We are seeking a Junior to Mid-Level
IT Security Analyst
with hands-on exposure to
AI, Generative AI, and Agentic AI security . This role supports a Product Security organization focused on implementing security guardrails for AI-enabled applications. You will work closely with Data, AI, and Product teams to secure machine learning pipelines, large language models, and agent-based systems in a cloud-native enterprise environment.
Key Responsibilities Embed security controls into
AI/ML models, LLM-based applications, and agentic workflows
across the SDLC Conduct security reviews of
Generative AI, traditional ML models, and supporting data pipelines Identify and mitigate AI-specific threats such as
prompt injection, data poisoning, model abuse, and insecure agents Support and apply AI security standards aligned with
NIST, ISO, and emerging AI governance frameworks Partner with legal, compliance, and privacy teams on
AI risk management and regulatory requirements Assist in evaluating and operating
AI security and observability tools
for model monitoring and data protection Contribute to internal guidance and training on
secure AI development practices
Required Qualifications Bachelors degree in Computer Science, Information Security, or related discipline 2+ years of experience in
cybersecurity , with exposure to
AI/ML environments Experience with
cloud-native security concepts
and threat modeling Understanding of AI/ML concepts including
model training, inference, data labeling, and adversarial attacks Familiarity with core security domains such as
authentication, encryption, network security, and IAM Strong communication and collaboration skills within
agile or SAFe-based teams
Preferred / Nice-to-Have Skills Experience with
AI security platforms
such as
Zenity
or
HiddenLayer Familiarity with
Microsoft security and AI governance tooling , including: Microsoft Defender for Cloud Microsoft Defender for Cloud Apps Azure AI Content Safety Microsoft Purview (data governance / DLP) Exposure to
Power Platform, Power BI, or low-code environments , especially implementing
DLP or data governance controls Experience with
AI model governance or AI security programs Security or cloud certifications (e.g.,
CCSK, CEH , or AI-focused credentials) Scripting or automation experience for
security testing and validation
AI & Emerging Technology Security (Contract)
We are seeking a Junior to Mid-Level
IT Security Analyst
with hands-on exposure to
AI, Generative AI, and Agentic AI security . This role supports a Product Security organization focused on implementing security guardrails for AI-enabled applications. You will work closely with Data, AI, and Product teams to secure machine learning pipelines, large language models, and agent-based systems in a cloud-native enterprise environment.
Key Responsibilities Embed security controls into
AI/ML models, LLM-based applications, and agentic workflows
across the SDLC Conduct security reviews of
Generative AI, traditional ML models, and supporting data pipelines Identify and mitigate AI-specific threats such as
prompt injection, data poisoning, model abuse, and insecure agents Support and apply AI security standards aligned with
NIST, ISO, and emerging AI governance frameworks Partner with legal, compliance, and privacy teams on
AI risk management and regulatory requirements Assist in evaluating and operating
AI security and observability tools
for model monitoring and data protection Contribute to internal guidance and training on
secure AI development practices
Required Qualifications Bachelors degree in Computer Science, Information Security, or related discipline 2+ years of experience in
cybersecurity , with exposure to
AI/ML environments Experience with
cloud-native security concepts
and threat modeling Understanding of AI/ML concepts including
model training, inference, data labeling, and adversarial attacks Familiarity with core security domains such as
authentication, encryption, network security, and IAM Strong communication and collaboration skills within
agile or SAFe-based teams
Preferred / Nice-to-Have Skills Experience with
AI security platforms
such as
Zenity
or
HiddenLayer Familiarity with
Microsoft security and AI governance tooling , including: Microsoft Defender for Cloud Microsoft Defender for Cloud Apps Azure AI Content Safety Microsoft Purview (data governance / DLP) Exposure to
Power Platform, Power BI, or low-code environments , especially implementing
DLP or data governance controls Experience with
AI model governance or AI security programs Security or cloud certifications (e.g.,
CCSK, CEH , or AI-focused credentials) Scripting or automation experience for
security testing and validation