Senior AI Cyber Security Engineer
ImmunityBio, Inc.
June 26, 2026
On-site
El Segundo, CA
IT
Position Summary
The Senior AI Cybersecurity Engineer secures AI/ML systems end-to-end—from data pipelines and model training to deployment, monitoring, and abuse prevention. Partners with data science, platform, product, and security teams to design secure AI architectures, threat model AI/ML use cases, detect/respond to AI-driven and AI-targeting attacks, and define secure development/governance practices.
Essential Functions
- Design/implement security controls for AI/ML platforms (training environments, inference services, data pipelines, feature stores).
- Threat model AI systems (model theft, data poisoning, prompt injection, model inversion, abuse/misuse).
- Build/maintain security tooling and automation to detect/prevent AI attacks (adversarial inputs, prompt injection chains, anomalous usage).
- Integrate security into AI development lifecycle (secure coding, model validation, testing, red teaming).
- Harden third-party AI integrations (LLM APIs, vector DBs, orchestration frameworks, agents), including authn/authz, data handling, logging.
- Ensure AI infrastructure security best practices (Kubernetes, GPU clusters, model registries, CI/CD) and compliance.
- Define monitoring for abuse detection, drift/anomaly alerts, access patterns, and security telemetry.
- Support incident response investigations involving AI systems (logs, traffic, model behavior, compromise).
- Define policies/guardrails for responsible and secure internal AI use (data classification, allowed use cases, evaluation).
- Mentor engineers; stay current on AI threats/regulations and translate into recommendations.
- Create/adhere to SOPs, process improvements, and templates.
Education & Experience (Required)
- Bachelor’s degree with 8+ years relevant experience, OR high school diploma/equivalent with 12+ years.
- 5+ years hands-on security engineering (application/product/cloud/infrastructure) with production security controls.
- Practical AI/ML experience (ML pipelines/LLM apps/vector search/MLOps) as security or closely with ML teams.
- Experience with authentication/authorization, secrets management, network segmentation, and secure CI/CD for services/APIs.
Skills (Preferred)
- Secure LLM/genAI app security (RAG, AI agents, chatbots, code assistants).
- Security logging/observability (SIEM, data lakes, security analytics) and detections for AI threats.
- Relevant certifications (cloud security/offensive/AI-focused).
Knowledge/Skills
- Cloud/container/orchestration knowledge (AWS/Azure/GCP; Docker/Kubernetes) for AI workloads.
- AI/ML threats: data poisoning, model theft/exfiltration, adversarial examples, model inversion, prompt injection, jailbreaks, gen-model abuse.
- Programming: Python preferred (Go/Java also valuable).
- Secure SDLC, code review, security design reviews.
- Ability to communicate risks/tradeoffs to technical and non-technical stakeholders.
- Hands-on ML stacks (PyTorch/TensorFlow/scikit-learn) and/or platforms (SageMaker/Vertex AI/Azure ML/on-prem).
- Familiarity with AI security/safety frameworks (e.g., NIST AI RMF, ISO/IEC).
- Background in red teaming/offensive security for applications/APIs/AI systems.
Working Environment
- Onsite; Monday–Friday, standard business hours (flexible with manager approval).
- Mobility and ability to lift/carry up to 20 pounds.
Benefits
- Discretionary bonus and equity award.
- Medical, dental, and vision plan options; wellness programs; EAP; life/AD&D and disability; healthcare/dependent care FSAs; 401(k) match; 529; voluntary legal/identity theft/pet insurance/discounts; PTO (11 holidays; exempt unlimited PTO; non-exempt: 10 vacation days, 56 hours health pay, 2 personal days, 1 cultural day).
Application Instructions
- Application window anticipated to close 60 days from posting, or sooner if filled/closed.
The Senior AI Cybersecurity Engineer secures AI/ML systems end-to-end—from data pipelines and model training to deployment, monitoring, and abuse prevention. Partners with data science, platform, product, and security teams to design secure AI architectures, threat model AI/ML use cases, detect/respond to AI-driven and AI-targeting attacks, and define secure development/governance practices.
Essential Functions
- Design/implement security controls for AI/ML platforms (training environments, inference services, data pipelines, feature stores).
- Threat model AI systems (model theft, data poisoning, prompt injection, model inversion, abuse/misuse).
- Build/maintain security tooling and automation to detect/prevent AI attacks (adversarial inputs, prompt injection chains, anomalous usage).
- Integrate security into AI development lifecycle (secure coding, model validation, testing, red teaming).
- Harden third-party AI integrations (LLM APIs, vector DBs, orchestration frameworks, agents), including authn/authz, data handling, logging.
- Ensure AI infrastructure security best practices (Kubernetes, GPU clusters, model registries, CI/CD) and compliance.
- Define monitoring for abuse detection, drift/anomaly alerts, access patterns, and security telemetry.
- Support incident response investigations involving AI systems (logs, traffic, model behavior, compromise).
- Define policies/guardrails for responsible and secure internal AI use (data classification, allowed use cases, evaluation).
- Mentor engineers; stay current on AI threats/regulations and translate into recommendations.
- Create/adhere to SOPs, process improvements, and templates.
Education & Experience (Required)
- Bachelor’s degree with 8+ years relevant experience, OR high school diploma/equivalent with 12+ years.
- 5+ years hands-on security engineering (application/product/cloud/infrastructure) with production security controls.
- Practical AI/ML experience (ML pipelines/LLM apps/vector search/MLOps) as security or closely with ML teams.
- Experience with authentication/authorization, secrets management, network segmentation, and secure CI/CD for services/APIs.
Skills (Preferred)
- Secure LLM/genAI app security (RAG, AI agents, chatbots, code assistants).
- Security logging/observability (SIEM, data lakes, security analytics) and detections for AI threats.
- Relevant certifications (cloud security/offensive/AI-focused).
Knowledge/Skills
- Cloud/container/orchestration knowledge (AWS/Azure/GCP; Docker/Kubernetes) for AI workloads.
- AI/ML threats: data poisoning, model theft/exfiltration, adversarial examples, model inversion, prompt injection, jailbreaks, gen-model abuse.
- Programming: Python preferred (Go/Java also valuable).
- Secure SDLC, code review, security design reviews.
- Ability to communicate risks/tradeoffs to technical and non-technical stakeholders.
- Hands-on ML stacks (PyTorch/TensorFlow/scikit-learn) and/or platforms (SageMaker/Vertex AI/Azure ML/on-prem).
- Familiarity with AI security/safety frameworks (e.g., NIST AI RMF, ISO/IEC).
- Background in red teaming/offensive security for applications/APIs/AI systems.
Working Environment
- Onsite; Monday–Friday, standard business hours (flexible with manager approval).
- Mobility and ability to lift/carry up to 20 pounds.
Benefits
- Discretionary bonus and equity award.
- Medical, dental, and vision plan options; wellness programs; EAP; life/AD&D and disability; healthcare/dependent care FSAs; 401(k) match; 529; voluntary legal/identity theft/pet insurance/discounts; PTO (11 holidays; exempt unlimited PTO; non-exempt: 10 vacation days, 56 hours health pay, 2 personal days, 1 cultural day).
Application Instructions
- Application window anticipated to close 60 days from posting, or sooner if filled/closed.