Senior Application Security Researcher

A Senior Cybersecurity Specialist with AI expertise who will lead efforts to secure generative AI systems, implement LLM security frameworks, and develop strategies to protect against emerging AI-specific threats while ensuring regulatory compliance. This strategic role will directly impact the organization's ability to safely harness AI technologies while maintaining trust and data integrity, particularly in the implementation of our upcoming enterprise-wide LLM integration initiative.

Key Responsibilities

Conduct comprehensive security assessments for AI/LLM implementations, identifying vulnerabilities in prompt engineering, model architecture, and deployment pipelines

Develop and implement security controls specific to generative AI systems, including prompt injection defenses and data poisoning prevention

Lead red team exercises to test the resilience of AI systems against adversarial attacks

Collaborate with AI engineers to implement privacy-preserving techniques in model training and inference

Monitor and respond to emerging AI security threats including model inversion attacks, training data extraction, and inference manipulation

Ensure compliance with AI-specific regulations (GDPR, NIST AI RMF, EU AI Act) and ethical guidelines

Establish and maintain AI security governance frameworks and policies Protection of your proprietary codebases, models, and training data as a key responsibility (e.g. source code governance, secure model storage, AI-assisted coding tools and managing open-source dependency risks)

Required Qualifications

7+ years of experience in cybersecurity with at least 3 years focused on AI/ML security

Strong understanding of LLM architecture, training processes, and deployment models

Experience implementing security controls for generative AI applications

Proficiency in secure coding practices for AI systems

Knowledge of adversarial machine learning techniques and defenses

Familiarity with AI ethics frameworks and emerging regulations

Technical Skills

AI security tools and frameworks (e.g., AI Security Alliance tools, LLM security scanners, OWASP LLM Top 10)

Programming experience in Python and relevant ML frameworks

Cloud security for AI workloads (AWS, Azure, GCP)

Knowledge of secure MLOps practices

Experience with privacy-enhancing technologies for AI (differential privacy, federated learning)

Familiarity with model monitoring and security observability tools

Experience with securing vector databases and embedding pipelines could also be relevant.

Familiarity with the OECD principles

Soft Skills & Leadership

Ability to communicate complex AI security concepts to technical and non-technical stakeholders

Experience leading cross-functional teams and security initiatives

Strategic thinking and risk assessment capabilities

Mentorship experience to develop junior security professionals

Excellent problem-solving skills in high-pressure situations

Preferred Qualifications

CISSP certification (strongly preferred) along with other relevant certifications (CISM, Cloud Security)

Experience with responsible AI governance frameworks

Background in prompt engineering security or LLM red teaming

Publications or contributions to AI security standards or best practices

Experience working with AI ethics committees or review boards

Originally posted on Himalayas

Job Description

Job Summary

Key Responsibilities

Conduct comprehensive security assessments for AI/LLM implementations, identifying vulnerabilities in prompt engineering, model architecture, and deployment pipelines

Develop and implement security controls specific to generative AI systems, including prompt injection defenses and data poisoning prevention

Lead red team exercises to test the resilience of AI systems against adversarial attacks

Collaborate with AI engineers to implement privacy-preserving techniques in model training and inference

Monitor and respond to emerging AI security threats including model inversion attacks, training data extraction, and inference manipulation

Ensure compliance with AI-specific regulations (GDPR, NIST AI RMF, EU AI Act) and ethical guidelines

Required Qualifications

7+ years of experience in cybersecurity with at least 3 years focused on AI/ML security

Strong understanding of LLM architecture, training processes, and deployment models

Experience implementing security controls for generative AI applications

Proficiency in secure coding practices for AI systems

Knowledge of adversarial machine learning techniques and defenses

Familiarity with AI ethics frameworks and emerging regulations

Technical Skills

AI security tools and frameworks (e.g., AI Security Alliance tools, LLM security scanners, OWASP LLM Top 10)

Programming experience in Python and relevant ML frameworks

Cloud security for AI workloads (AWS, Azure, GCP)

Knowledge of secure MLOps practices

Experience with privacy-enhancing technologies for AI (differential privacy, federated learning)

Familiarity with model monitoring and security observability tools

Experience with securing vector databases and embedding pipelines could also be relevant.

Familiarity with the OECD principles

Soft Skills & Leadership

Ability to communicate complex AI security concepts to technical and non-technical stakeholders

Experience leading cross-functional teams and security initiatives

Strategic thinking and risk assessment capabilities

Mentorship experience to develop junior security professionals

Excellent problem-solving skills in high-pressure situations

Preferred Qualifications

CISSP certification (strongly preferred) along with other relevant certifications (CISM, Cloud Security)

Experience with responsible AI governance frameworks

Background in prompt engineering security or LLM red teaming

Publications or contributions to AI security standards or best practices

Experience working with AI ethics committees or review boards

Originally posted on Himalayas

Job Description

Job Summary

Key Responsibilities

Conduct comprehensive security assessments for AI/LLM implementations, identifying vulnerabilities in prompt engineering, model architecture, and deployment pipelines

Develop and implement security controls specific to generative AI systems, including prompt injection defenses and data poisoning prevention

Lead red team exercises to test the resilience of AI systems against adversarial attacks

Collaborate with AI engineers to implement privacy-preserving techniques in model training and inference

Monitor and respond to emerging AI security threats including model inversion attacks, training data extraction, and inference manipulation

Ensure compliance with AI-specific regulations (GDPR, NIST AI RMF, EU AI Act) and ethical guidelines

Required Qualifications

7+ years of experience in cybersecurity with at least 3 years focused on AI/ML security

Strong understanding of LLM architecture, training processes, and deployment models

Experience implementing security controls for generative AI applications

Proficiency in secure coding practices for AI systems

Knowledge of adversarial machine learning techniques and defenses

Familiarity with AI ethics frameworks and emerging regulations

Technical Skills

AI security tools and frameworks (e.g., AI Security Alliance tools, LLM security scanners, OWASP LLM Top 10)

Programming experience in Python and relevant ML frameworks

Cloud security for AI workloads (AWS, Azure, GCP)

Knowledge of secure MLOps practices

Experience with privacy-enhancing technologies for AI (differential privacy, federated learning)

Familiarity with model monitoring and security observability tools

Experience with securing vector databases and embedding pipelines could also be relevant.

Familiarity with the OECD principles

Soft Skills & Leadership

Ability to communicate complex AI security concepts to technical and non-technical stakeholders

Experience leading cross-functional teams and security initiatives

Strategic thinking and risk assessment capabilities

Mentorship experience to develop junior security professionals

Excellent problem-solving skills in high-pressure situations

Preferred Qualifications

CISSP certification (strongly preferred) along with other relevant certifications (CISM, Cloud Security)

Experience with responsible AI governance frameworks

Background in prompt engineering security or LLM red teaming

Publications or contributions to AI security standards or best practices

Experience working with AI ethics committees or review boards

Originally posted on Himalayas

Job Description

Job Summary

Key Responsibilities

Conduct comprehensive security assessments for AI/LLM implementations, identifying vulnerabilities in prompt engineering, model architecture, and deployment pipelines

Develop and implement security controls specific to generative AI systems, including prompt injection defenses and data poisoning prevention

Lead red team exercises to test the resilience of AI systems against adversarial attacks

Collaborate with AI engineers to implement privacy-preserving techniques in model training and inference

Monitor and respond to emerging AI security threats including model inversion attacks, training data extraction, and inference manipulation

Ensure compliance with AI-specific regulations (GDPR, NIST AI RMF, EU AI Act) and ethical guidelines

Required Qualifications

7+ years of experience in cybersecurity with at least 3 years focused on AI/ML security

Strong understanding of LLM architecture, training processes, and deployment models

Experience implementing security controls for generative AI applications

Proficiency in secure coding practices for AI systems

Knowledge of adversarial machine learning techniques and defenses

Familiarity with AI ethics frameworks and emerging regulations

Technical Skills

AI security tools and frameworks (e.g., AI Security Alliance tools, LLM security scanners, OWASP LLM Top 10)

Programming experience in Python and relevant ML frameworks

Cloud security for AI workloads (AWS, Azure, GCP)

Knowledge of secure MLOps practices

Experience with privacy-enhancing technologies for AI (differential privacy, federated learning)

Familiarity with model monitoring and security observability tools

Experience with securing vector databases and embedding pipelines could also be relevant.

Familiarity with the OECD principles

Soft Skills & Leadership

Ability to communicate complex AI security concepts to technical and non-technical stakeholders

Experience leading cross-functional teams and security initiatives

Strategic thinking and risk assessment capabilities

Mentorship experience to develop junior security professionals

Excellent problem-solving skills in high-pressure situations

Preferred Qualifications

CISSP certification (strongly preferred) along with other relevant certifications (CISM, Cloud Security)

Experience with responsible AI governance frameworks

Background in prompt engineering security or LLM red teaming

Publications or contributions to AI security standards or best practices

Experience working with AI ethics committees or review boards

Originally posted on Himalayas