This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a ML Security Engineer based in the United States.
This role focuses on securing the next generation of AI-powered systems, with an emphasis on large language models, machine learning pipelines, and intelligent applications operating at scale.
You will design and implement security controls that protect AI systems from emerging threats such as prompt injection, model abuse, and data exfiltration.
The position sits at the intersection of cybersecurity and machine learning, requiring both strong security engineering fundamentals and practical understanding of modern AI architectures.
You will help define how AI systems are hardened, monitored, and governed across development and production environments.
A key part of the role involves building threat models, guardrails, and detection systems tailored specifically for AI workloads.
You will collaborate with engineering, privacy, and compliance teams to ensure secure, responsible deployment of AI capabilities.
This is a highly technical and forward-looking role in a fast-evolving environment where security directly enables safe AI innovation.
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a ML Security Engineer based in the United States.
This role focuses on securing the next generation of AI-powered systems, with an emphasis on large language models, machine learning pipelines, and intelligent applications operating at scale.
You will design and implement security controls that protect AI systems from emerging threats such as prompt injection, model abuse, and data exfiltration.
The position sits at the intersection of cybersecurity and machine learning, requiring both strong security engineering fundamentals and practical understanding of modern AI architectures.
You will help define how AI systems are hardened, monitored, and governed across development and production environments.
A key part of the role involves building threat models, guardrails, and detection systems tailored specifically for AI workloads.
You will collaborate with engineering, privacy, and compliance teams to ensure secure, responsible deployment of AI capabilities.
This is a highly technical and forward-looking role in a fast-evolving environment where security directly enables safe AI innovation.
Accountabilities:
- Design and implement security controls tailored to LLMs, AI applications, and machine learning infrastructure.
- Develop threat models addressing risks such as prompt injection, jailbreaks, model abuse, and data leakage.
- Build and deploy guardrails, filtering mechanisms, and policy enforcement layers around AI model endpoints.
- Implement runtime monitoring, detection, and response systems for adversarial or malicious AI usage.
- Secure ML pipelines including training data integrity, provenance tracking, and access control enforcement.
- Design protections for sensitive data handling, retention policies, and redaction in AI workflows.
- Lead AI-focused red teaming exercises and drive remediation of identified vulnerabilities.
- Collaborate with cross-functional teams to ensure compliance with privacy, legal, and regulatory requirements.
- Develop logging, observability, and incident response strategies for AI-specific security events.
- Evaluate third-party AI services and open-source models to ensure secure integration and usage.
- Bachelor’s or Master’s degree in Computer Science, Cybersecurity, or a related field.
- 6+ years of security engineering experience, including hands-on exposure to AI/ML systems.
- Strong understanding of large language models, modern AI architectures, and their security risks.
- Proven experience in application security, threat modeling, and secure system design.
- Familiarity with adversarial ML concepts such as prompt injection, model poisoning, and jailbreak techniques.
- Proficiency in Python and at least one systems programming language (e.g., Go, C++, or Java).
- Strong knowledge of cloud security principles and modern infrastructure security controls.
- Experience designing identity, authorization, and multi-tenant security models.
- Ability to lead incident response and security investigations for complex technical systems.
- Excellent communication skills and ability to translate technical risks into actionable insights.
- Experience with AI red teaming, security research, or published work in AI security is a plus.
- Competitive salary range of $100,000–$150,000 annually
- 100% remote work across the continental United States
- Full-time W2 employment with no third-party contracting structure
- Medical, dental, vision, and life insurance coverage
- 401(k) retirement plan and financial wellness benefits
- Paid time off and holidays
- Annual performance and incentive opportunities
- Career growth in a rapidly evolving AI security domain
- Exposure to cutting-edge machine learning and LLM security challenges
- Inclusive, equal-opportunity workplace with strong focus on diversity.