Senior Security Engineer, Artificial Intelligence

SRI Resources; Irving (TX); On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Medical, dental, and vision coverage

401(k) with company match

Short-term disability

Life insurance with AD&D

Job summary

Cybersecurity Jobs is seeking an experienced Security Engineer to design and deliver security controls for AI systems across the full lifecycle—from secure model development to detection and incident response. You will define security requirements across model development, training, deployment, and monitoring, and lead threat modeling of AI systems and features.

You will establish secure-by-design patterns for model endpoints, prompts, RAG pipelines, and agent workflows.

Qualifications

• 8+ years in Information Security, or 5+ years in security engineering, app security, cloud security or detection engineering if no degree
• At least 3 years of AI Security experience
• Experience securing LLM-based apps, RAG systems, or agentic workflows
• Familiarity with adversarial ML concepts: prompt injection, model inversion, model extraction
• Hands-on experience with at least one programming language (Python preferred)
• Strong understanding of AI/LLMs, API security, identity, secrets management, and cloud controls
• Experience building security controls into CI/CD pipelines
• Proven ability to lead cross-functional security work with engineering and product teams
• Excellent ability to communicate complex tech to both technical and non-technical stakeholders
• Proven leadership to influence and drive change

Responsibilities

• Define security requirements across model development, training, deployment, and monitoring
• Threat model AI systems and features, including abuse and misuse scenarios
• Establish secure-by-design patterns for model endpoints, prompts, RAG pipelines, and agent workflows
• Validate controls for model access, rate limiting, tenant isolation, and secrets management
• Classify and control training data, fine-tuning data, prompts, and retrieved context
• Develop CI and CD checks for AI assets, including scanning, signing, and policy enforcement
• Create logging standards for model requests, responses, tool calls, and retrieval events
• Develop detections for prompt injection, data exfiltration attempts, model extraction signals, and anomalous usage
• Develop incident response playbooks for AI events, including containment and rollback plans
• Run security testing for AI features, including red teaming and structured adversarial testing
• Create practical AI security standards, patterns, and reference architectures
• Lead risk reviews for new AI features and vendor assessments for AI services
• Train engineering and data science teams on secure AI patterns and common attack paths

Skills

Leadership capabilities

Cross-functional collaboration

Communication

Threat modeling

Security engineering

Education

Bachelor's degree in Cybersecurity or related field

Master's degree in Cybersecurity or related field

Tools

AWS

Azure

GCP

Kubernetes

Docker

GitHub Actions

GitLab CI

Azure DevOps

Terraform

SIEM

EDR

WAF

API Gateways

Secrets Managers

Python

Vector Databases

Model Registries

ML Pipelines

Job description

Design and deliver security controls for AI systems across the full lifecycle, from secure model development to detection and incident response.

Responsibilities

• Define security requirements across model development, training, evaluation, deployment, and monitoring
• Threat model AI systems and AI features, covering abuse cases and misuse scenarios
• Establish secure-by-design patterns for model endpoints, prompts, RAG pipelines, and agent workflows
• Validate controls for model access, rate limiting, tenant isolation, and secrets management
• Classify and control training data, fine-tuning data, prompts, and retrieved context
• Implement guardrails to prevent sensitive data exposure, including PII and PCI data
• Define retention, deletion, and lineage requirements for AI datasets and outputs
• Partner with Privacy and Legal on data handling, regulatory expectations, and third-party data use
• Harden AI platforms, GPU and container workloads, model registries, and artifact stores
• Assess risks in third-party models, libraries, embeddings, and model hosting services
• Define integrity controls for model artifacts, evaluation sets, and pipeline automation
• Build CI and CD checks for AI assets, including scanning, signing, and policy enforcement
• Create logging standards for model requests, responses, tool calls, and retrieval events
• Develop detections for prompt injection, data exfiltration attempts, model extraction signals, and anomalous usage
• Develop incident response playbooks for AI events, including containment and rollback plans
• Run security testing for AI features, including red teaming and structured adversarial testing
• Create practical AI security standards, patterns, and reference architectures
• Define KPIs such as reduction in sensitive output leakage, time to detect misuse, and policy coverage
• Lead risk reviews for new AI features and vendor assessments for AI services
• Train engineering and data science teams on secure AI patterns and common attack paths

Requirements

• 8 years of experience in Information Security, or 5+ years in security engineering, application security, cloud security, or detection engineering if there is no degree
• At least 3 years of experience in AI Security
• Experience securing LLM-based applications, RAG systems, or agentic workflows
• Familiarity with adversarial ML concepts, including prompt injection, model inversion, and model extraction
• Experience with one or more cloud platforms: AWS, Azure, or GCP
• Hands-on experience with at least one programming language, with Python preferred
• Strong understanding of AI, LLMs, API security, identity, secrets management, and cloud controls
• Experience building security controls into CI and CD pipelines
• Proven ability to lead cross-functional security work with engineering and product teams
• Communicate complex technical concepts to technical and non-technical stakeholders
• Communicate with leadership and escalates with proactive, clear, data-driven insight, highlighting risks, roadblocks, and solutions
• Proven leadership capabilities to influence and drive change

Technologies

• AWS, Azure, GCP
• Kubernetes, Docker
• GitHub Actions, GitLab CI, Azure DevOps
• Terraform
• SIEM, EDR, WAF, API gateways, secrets managers
• Python
• Model gateways, vector databases, model registries, ML pipelines
• PII, PCI

Examples of Work and Technical Scope

• Secure an LLM gateway with authentication, authorization, quotas, content filtering, and audit logging
• Add prompt injection defenses for an agent using tools like web search and internal APIs
• Implement retrieval filtering, context redaction, and output scanning for a RAG application
• Build model artifact signing and verification into the release pipeline
• Create SIEM detections for abnormal model usage, including model scraping patterns

Preferred Qualifications

• Bachelor's degree in Cybersecurity, Artificial Intelligence, Computer Science, or related highly technical field
• Experience with Kubernetes and container security
• Master's degree in Cybersecurity, Artificial Intelligence, Computer Science, or related highly technical field
• AI/ML certifications such as Microsoft Azure AI Engineer, AWS ML Specialty, GIAC Machine Learning Engineer, ISC2 Building AI Strategy
• Experience with security telemetry and detections in SIEM or EDR platforms

Benefits

• Medical, dental, and vision coverage
• 401(k) with company match
• Short-term disability
• Life insurance with AD&D

Location and Job Type

• Irving, TX (onsite)
• Contract