[Remote] AI Security Engineer

Note: The job is a remote job and is open to candidates in USA. Bright Vision Technologies is a forward-thinking software development company dedicated to building innovative solutions that help businesses automate and optimize their operations. We are seeking an AI Security Engineer to lead the design and implementation of security controls and threat models specifically tailored to AI and machine learning systems. The role involves addressing unique security challenges and requires strong security engineering fundamentals along with a deep understanding of modern AI systems.ResponsibilitiesDefine and implement security controls specifically targeting LLM and AI-powered application risksBuild threat models for AI systems, including prompt injection, jailbreaks, data exfiltration, and abuse patternsDesign and deploy guardrails, content filters, and policy enforcement layers around model endpointsImplement runtime detection and response capabilities for adversarial prompts and abusive behaviorSecure training and fine-tuning pipelines, including data provenance, integrity, and access controlsDesign controls for sensitive data handling, retention, and redaction in LLM workflowsLead red-team exercises against AI systems and drive remediation of identified weaknessesEvaluate and harden third-party AI services and open-source AI components used internallyImplement identity, authorization, and tenant-isolation patterns for multi-tenant AI servicesDrive supply chain security for ML artifacts including weights, datasets, and inference dependenciesCollaborate with privacy, legal, and compliance teams to ensure AI systems meet regulatory obligationsDevelop monitoring, logging, and detection strategies tailored to AI workloadsLead incident response for AI-specific security events and drive durable improvementsStay current with adversarial ML, LLM security research, and emerging regulatory developmentsSkillsBachelor's or Master's degree in Computer Science, Cybersecurity, or a related disciplineSix or more years of security engineering experience, including significant work on AI or ML systemsStrong understanding of LLM internals, modern AI architectures, and common failure modesHands-on experience designing security controls for AI-powered applicationsDeep knowledge of application security, identity, and cryptography fundamentalsExperience with threat modeling and security architecture review processesFamiliarity with adversarial ML, prompt injection, and model abuse researchProficiency in Python and at least one systems languageStrong understanding of cloud security and modern infrastructure controlsExcellent written and verbal communication skillsPublications, talks, or CTF participation in AI security topicsExperience with red-teaming LLM-based productsFamiliarity with privacy-preserving ML techniques such as differential privacyExposure to regulated industries with strict data handling requirementsOpen-source contributions to AI security toolingBenefitsFull-time, direct W2 with Bright Vision Technologies (no C2C, no 1099, no third-party)Competitive base salary commensurate with experience, plus benefits.No new H1B sponsorship available.H1B transfers welcomed for qualified candidates.Company OverviewBright Vision Technologies is an information technology company that offers software development, AI, and cybersecurity services. It was founded in 2020, and is headquartered in Bridgewater, New Jersey, USA, with a workforce of 51-200 employees. Its website is https://bvteck.com.