Remote AI Risk Engineer - Threat Modeling & Safeguards

Bright Vision Technologies; Fishers (IN); Remote; USD 100,000 - 150,000; Full time

Job summary

Bright Vision Technologies is seeking an AI Risk Engineer to design and implement security controls for AI/ML systems, focusing on LLMs and model APIs. You will build threat models, deploy guardrails, and drive incident response capabilities across AI workloads.

The role requires strong security engineering fundamentals, hands-on defense design for AI-powered applications, and collaboration with privacy and compliance teams. 100% remote (continental US) with sponsorship considerations noted.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Cybersecurity, or a related discipline.
• Six or more years of security engineering experience, including AI/ML systems.
• Strong understanding of LLM internals, modern AI architectures, and failure modes.
• Hands-on experience designing security controls for AI-powered apps.
• Familiarity with threat modeling and security architecture reviews.
• Proficiency in Python and at least one systems language.
• Cloud security knowledge and modern infrastructure controls.
• Excellent written and verbal communication skills.

Responsibilities

• Define and implement security controls for LLM and AI-powered risks.
• Build threat models for AI systems including prompt injection and data exfiltration.
• Design guardrails, content filters, and policy enforcement for model endpoints.
• Implement runtime detection and response for adversarial prompts.
• Secure training/fine-tuning pipelines with data provenance and access controls.
• Handle data retention and redaction in LLM workflows.
• Lead red-team exercises and drive remediation of weaknesses.
• Evaluate third-party AI services and open-source AI components.
• Implement identity, authorization, and tenant isolation for multi-tenant AI services.
• Drive supply chain security for ML artifacts (weights, datasets, deps).
• Collaborate with privacy/legal/compliance to meet regulatory obligations.
• Develop monitoring, logging, and detection strategies for AI workloads.
• Lead incident response for AI-specific security events and improvements.
• Stay current with adversarial ML, LLM security research, and regulatory developments.

Skills

Threat modeling

Security engineering

AI/ML security concepts

LLM internals knowledge

Python

Systems language

Communication skills

Security architecture review

Education

Bachelor’s or Master’s degree in Computer Science or Cybersecurity

Tools

Python

Systems languages

Job description

Bright Vision Technologies is seeking an AI Risk Engineer to design and implement security controls for AI/ML systems, focusing on LLMs and model APIs. You will build threat models, deploy guardrails, and drive incident response capabilities across AI workloads.

The role requires strong security engineering fundamentals, hands-on defense design for AI-powered applications, and collaboration with privacy and compliance teams. 100% remote (continental US) with sponsorship considerations noted.