AI Security Engineer (GRC – Healthcare) | W2 Contract | USC Only |

The Job

TheAISecurity Engineer (GRC) serves as the organizations dedicated subject matter expert at the intersection of artificial intelligence and cybersecurity within a regulated healthcare environment. This role is responsible for evaluatingAIvendors and technologies establishing and enforcing secureAIimplementation standards and providing hands-on guidance to development and engineering teams adoptingAIplatforms such as Microsoft Copilot Studio AzureAIFoundry Snowflake Cortex Claude Code and other large language model (LLM)-powered tooling.

Operating within the HIPAA-regulated landscape this analyst will ensureAIintegrations including Model Context Protocol (MCP) servers agentic workflows command-line interfaces (CLIs) APIs and third-partyAIextensions are architected and deployed in a manner consistent with NISTAIRMF HITRUST and organizational security policies. The role acts as a trusted advisor security gatekeeper and enabler for responsibleAIadoption across the enterprise.

You Will

1. AIVendor & Technology Evaluation

• Lead structured security assessments ofAIvendors platforms and tools prior to organizational adoption or renewal
• Evaluate vendor data handling practices model trainingtransparencyanddata residency
• Assess the security posture ofAIplatforms including:
• Microsoft Copilot Studio plugin trust boundaries connector authentication Power Platform DLP policies
• AzureAIFoundry model deployment pipelines private endpoint configuration managed identity usage
• Snowflake Cortex data access controls inAI-generated SQL Snowpark security role-based privilege enforcement Cortex function access policies and query result exposure risks
• Claude Code & Anthropic APIs system prompt injection risks tool use / agentic permissions data retention settings
• GitHub Copilot Cursor and otherAI-assisted development tools code telemetry and secret leakage exposure
• Produce written Vendor Security Assessment Reports (VSARs) including risk ratings compensating controls and recommendations
• Maintain anAItechnology registry with risk classifications and review cadence schedules

2. Secure AIImplementation Guidance for Development Teams

• Serve as the embedded security advisor to software engineering data science and clinical informatics teams adoptingAItooling
• Define and enforce secure-by-default configurations forAIdevelopment environments and agentic systems
• Review and approve MCP server configurations ensuring:
• Tool definitions follow least-privilege principles no excessive file system network or shell access
• Server authentication uses OAuth 2.0 /mTLSand does not rely on static API keys stored in plaintext
• Transport layer security (TLS 1.2) is enforced on all MCP server communications
• Prompt injection attack surfaces areidentifiedand mitigated in tool descriptions and system prompts
• Logging and audit trails are enabled for all MCP tool invocations touching PHI or sensitive data
• Establish CLI security standards forAI-assisted development tools (Claude Code CLI GitHub Copilot CLI Azure Developer CLI) including credential hygiene shell history scrubbing and token scope minimization
• Conduct secure code review forAIintegration code with focus on prompt injection insecure deserialization and unsafe agentic action chains
• Develop andmaintaina library of reference architectures secure configuration templates and implementation checklists for approvedAIplatforms

3. AIRisk Management & Compliance

• Maintainthe organizationsAIRisk Register aligned with NISTAIRMF (Govern Map Measure Manage)
• EnsureAIdeploymentscomply withHIPAA Security Rule (45 CFR 164) HITECH Act obligations and applicable state privacy laws
• ConductAI-specific Threat Modeling (STRIDE / PASTA) and red-team exercises targeting:
• Prompt injection and jailbreak scenarios
• Indirect prompt injection via external data sources (email documents web retrieval)
• Model inversion and membership inference attacks on fine-tuned healthcare models
• Data exfiltration through agentic tool chains
• Track emergingAIthreats and threat actor TTPs relevant to healthcareAIsystems via MITRE ATLAS and sector ISACs
• Participate inAIgovernance committee meetings and contributeAIsecurity perspectives to organizationalAIpolicies

4. SecurityIntegration Reviews

• ReviewAIintegration architectures for network segmentation data flow and trust boundary enforcement
• Validate that PHI is never transmitted to externalAImodels without de-identification or explicit BAA coverage
• Assess retrieval-augmented generation (RAG) architectures for unauthorized data access and embedding extraction risks
• Evaluate agenticAIworkflows and multi-agent orchestration systems for privilege escalation and uncontrolled action chains
• Provide security sign-off onAIinfrastructure as part of the Change Advisory Board (CAB) process

5. Training Awareness & Policy

• DevelopAIsecurity training curricula for developers data engineers clinical staff and IT personnel
• Author andmaintain AIsecurity policiesincluding:Acceptable Use of GenerativeAIAIVendor Onboarding Standards MCP and Agentic System Security Policy and Sensitive Data Handling inAIContexts
• Publish internal guidance and threat intelligence briefings tailored to clinical and technical audiences

Your Qualifications

• Bachelors degree in Cybersecurity Computer Science Information Systems or a closely related field
• Masters degree preferred; equivalent professional experience considered
• 7 years of progressive experience in information security with a minimum of 2 years focused onAI/ML security or appliedAItechnology evaluation
• Demonstrated hands-on experience with one or more of the following: Copilot Studio AzureAIFoundry Claude / Anthropic APIs OpenAI API GitHub Copilot or LLM agentic frameworks (LangChain AutoGen Semantic Kernel)
• Experience working in a HIPAA-regulated environment; healthcare industry background strongly preferred
• Proven track record conducting vendor risk assessments and producing executive-level risk documentation
• Deep understanding of LLM attack surface: prompt injection indirect prompt injection system prompt extraction and model manipulation
• Familiarity withAIred-teaming methodologies and tools (Garak PyRIT PromptBench)
• Knowledge of OWASP Top 10 for LLM Applications
• Understanding ofAImodel lifecycle risks: training data poisoning supply chain risks in model registries (Hugging Face Azure Model Catalog)
• Ability to audit and secure Model Context Protocol (MCP) server implementations including:
• Reviewing tool definitions and permissions for least-privilege violations
• Validating authentication mechanisms (no hardcoded credentials proper token scoping)
• Assessing stdio vs. SSE transport security implications
• Identifying SSRF and command injection risks in custom MCP toolimplementations
• Experience securingAICLIs including credential storage environment variable exposure and shell integration risks
• Knowledge of agentic permission models understanding whenAIagents should require human-in-the-loop approval
• Ability to evaluate multi-stepAIworkflow chains for unintended capability escalation
• Microsoft Copilot Studio: Plugin manifest security review connector authentication sensitivity label enforcement
• AzureAIFoundry: Managed identity configuration private endpoints content filtering policy management model deployment governance
• Snowflake Cortex: SecuringAI-generated SQL and Cortex LLM functions Snowpark container security column-level data masking network policy enforcement and OAuth integration for service accounts
• Claude Code: System prompt construction tool-use permission hardening CLI credential isolation API key scoping
• GitHub Copilot Enterprise: Telemetry settings suggestion filtering for secrets IDE extension trust policies
• Strong grounding in identity and access management OAuth 2.0 OIDC SAML managed identities workload identity federation
• API security: authentication schemes rate limiting input validation and output sanitization forAIendpoints
• Network security: micro-segmentation private endpoints WAF configuration forAIservice ingress
• SIEM/SOAR integration forAIaudit log ingestion anomaly detection and automated response
• Threat modeling methodologies: STRIDE PASTA and application of MITRE ATT&CK and ATLAS frameworks
• Thorough understanding of HIPAA Security Rule requirements and how they apply toAIdata processing pipelines
• Experience with HITRUST CSF controls relevant toAIand cloud-based processing of ePHI
• Practical knowledge of NISTAIRisk Management Framework (AIRMF) Govern Map Measure Manage functions
• Familiarity with EUAIAct classifications and their implications for healthcareAIsystems (high-riskAIdesignation)
• Experience reviewing BAAs and DPAs forAIvendor engagements