AI Security Engineer

Bright Vision Technologies•East Brunswick, NJ

2d•$100,000 - $150,000•Remote

About The Position

Bright Vision Technologies is seeking an AI Security Engineer to lead the design and implementation of security controls, threat models, and incident response capabilities for AI and machine learning systems. The role addresses security challenges involving LLMs, model APIs, training data pipelines, and AI-powered applications, including prompt injection, model abuse, data exfiltration, and supply chain risks. The successful candidate will bring strong security engineering fundamentals and practical knowledge of modern AI systems, with hands-on experience designing defenses for AI applications and their supporting infrastructure. This is a full-time, direct W2 position that is 100% remote in the United States. The annual salary range is $100,000–$150,000. Applicants with eight or more years of relevant experience are sought. The company is unable to sponsor new H-1B visa petitions; U.S. citizens, Green Card holders, EAD holders, and H-1B transfer candidates are encouraged to apply.

Requirements

Bachelor’s or Master’s degree in Computer Science, Cybersecurity, or a related discipline.
Eight or more years of security engineering experience, including significant work on AI or ML systems.
Strong understanding of LLM internals, modern AI architectures, and common failure modes.
Hands-on experience designing security controls for AI-powered applications.
Deep knowledge of application security, identity, and cryptography fundamentals.
Experience with threat modeling and security architecture review processes.
Familiarity with adversarial ML, prompt injection, and model abuse research.
Proficiency in Python and at least one systems language.
Strong understanding of cloud security and modern infrastructure controls.
Excellent written and verbal communication skills.

Nice To Haves

Publications, talks, or CTF participation in AI security topics.
Experience with red-teaming LLM-based products.
Familiarity with privacy-preserving ML techniques such as differential privacy.
Exposure to regulated industries with strict data handling requirements.
Open-source contributions to AI security tooling.

Responsibilities

Define and implement security controls for risks in LLMs and AI-powered applications.
Build threat models for AI systems, including prompt injection, jailbreaks, data exfiltration, and abuse patterns.
Design and deploy guardrails, content filters, and policy enforcement layers around model endpoints.
Implement runtime detection and response capabilities for adversarial prompts and abusive behavior.
Secure training and fine-tuning pipelines, including data provenance, integrity, and access controls.
Design controls for sensitive data handling, retention, and redaction in LLM workflows.
Lead red-team exercises against AI systems and drive remediation of identified weaknesses.
Evaluate and harden third-party AI services and internally used open-source AI components.
Implement identity, authorization, and tenant-isolation patterns for multi-tenant AI services.
Drive supply chain security for ML artifacts, including weights, datasets, and inference dependencies.
Collaborate with privacy, legal, and compliance teams to ensure AI systems meet regulatory obligations.
Develop monitoring, logging, and detection strategies tailored to AI workloads.
Lead incident response for AI-specific security events and drive durable improvements.
Stay current with adversarial ML, LLM security research, and emerging regulatory developments.