AI Security Engineer

Description Position Details: Job Title: AI Security Engineer Job Type: Full-time Location: Remote, MD Dynanet Corporation Overview: Dynanet started with a focus on IT infrastructure and operations, helping organizations enhance their networks and overcome the limitations of 1990s technology. From strengthening communication channels to introducing innovative ways to collaborate and share information, Dynanet played a crucial role in shaping the early stages of digital transformation. The company’s efforts helped organizations build the very fabric of connectivity that now powers our modern world. Over the last three decades, Dynanet has grown into a trusted partner for organizations looking to innovate boldly and transform seamlessly. While technology continues to evolve and unlock new opportunities, for nearly 30 years, Dynanet remains committed to delivering cutting-edge solutions that drive lasting change for its customers. Through agility, foresight, and an unwavering dedication to excellence, Dynanet continues to empower organizations to thrive in a rapidly changing digital landscape. Our story is more than just a story of technology – it’s a story of vision, growth, and transformation that has shaped the past and continues to pave the way for the future. Requirements Roles & Responsibilities: Security Architecture for AI Workloads Design reference architectures for secure LLM/AI agent deployments across Azure, AWS, or hybrid environments. Establish defense-in-depth controls for model endpoints, vector databases, prompt routing, tools/plugins, and orchestration layers. Guardrails & Policy Enforcement Implement runtime guardrails including prompt injection defenses, output content filtering, PII detection/redaction, jailbreak prevention, and tool use restrictions. Codify enterprise policies (acceptable use, data residency, retention, secrets handling) into enforceable controls through middleware, gateways, and policy engines. Identity, Access & Data Protection Integrate Entra ID / Azure AD, OAuth/OIDC, and RBAC/ABAC models. Apply data security measures including DLP, encryption, key management/HSM, tokenization, and fine-grained data access for RAG pipelines. Secure SDLC for AI Embed threat modeling, secure coding, dependency scanning, secret scanning, and SAST/DAST into AI app pipelines. Define AI-specific code review checklists for prompt templates, tool bindings, and agent plans. Risk, Governance & Compliance Operationalize NIST AI RMF, ISO/IEC 27001 & 42001, SOC 2; align with FedRAMP, FISMA, NIST 800-53, and agency-specific controls. Maintain model cards, data lineage, evaluation reports, and audit trails for AI decisions and tool calls. AI Red Teaming & Evaluation Design adversarial tests for jailbreaks, prompt injections, data exfiltration attempts, and toxic outputs. Build automated evaluation harnesses and metrics such as hallucination rates, sensitive content occurrence, and tool misuse rates. Monitoring & Incident Response Establish observability for AI systems including privacy-aware logging, policy hits, model drift detection, cost governance, and anomalies. Define playbooks for AI incidents involving unsafe outputs, data leakage, compromised tools, or model endpoint abuse. Stakeholder Enablement Partner with Product and Engineering teams to safely accelerate new AI use cases. Provide training and guidance on responsible AI, secure agent design, and safe prompt engineering. Required Professional Skills: Cloud & AI Platforms Azure (Azure OpenAI, AI Studio, AKS, Key Vault, Entra ID, Defender), Microsoft Purview, and M365 Copilot governance. Experience with AWS (Bedrock, SageMaker, KMS) or GCP Vertex AI. LLM/Agent Security Hands-on guardrail implementation including content filters, safety classifiers, prompt injection defenses, jailbreak prevention, and tool whitelisting. Securing RAG pipelines and vector databases (Cosmos DB + pgvector/FAISS, Pinecone, Weaviate). Identity & Access OAuth/OIDC, SAML, SCIM, RBAC/ABAC; secrets management via Key Vault, Parameter Store, or Vault. Data Security Encryption, tokenization, redaction, differential privacy basics, DLP-based PII/PHI detection. Experience with data classification, retention, and lineage. Application Security & DevSecOps STRIDE threat modeling, secure coding, dependency scanning, secret scanning, SAST/DAST. CI/CD for AI apps (GitHub Actions/Azure DevOps), IaC (Bicep/Terraform), policy-as-code (OPA/Conftest/Azure Policy). Observability & Incident Response Logging with Azure Monitor/Sentinel, tracing, metrics, and automated AI evaluation pipelines integrated with SIEM/SOAR. Compliance & Governance Working knowledge of NIST AI RMF, ISO/IEC 42001, OWASP LLM Top 10, and public sector controls. Experience documenting controls, audits, and risk assessments. Programming & Frameworks Proficiency in Python or TypeScript/Node.js. Experience with agent/orchestration frameworks (LangChain, Semantic Kernel, Guidance, DSPy). Preferred Professional Skills: 5–8+ years in application/cloud security with 2+ years in AI/ML or LLM security. Experience enabling enterprise AI use cases or AI agents in regulated environments. Familiarity with Microsoft Copilot for M365 governance and Microsoft Purview. Experience with AI red teaming and building evaluation harnesses. Exposure to privacy regulations (HIPAA, GLBA, GDPR/CCPA) and public-sector compliance. Contributions to security frameworks or open-source guardrail tools Dynanet Team Requirements and Expectations: Possess Strong written and verbal communication skills. Highly organized with the ability to prioritize, balance, and effectively advance multiple competing priorities in a high-volume, fast-paced environment. Ability to interact in a professional and collaborative manner with fellow Dynanet Teammates and the clients, and business partners that we work with. Ability and desire to challenge and educate yourself to support and advance IT services delivery in the Federal agencies we serve. Excellent judgment and creative problem-solving skills. Respond to team member and client requests via email, MS teams, or other communication means during core business hours. Active listening skills to understand clients' needs, and collaboration skills to work with other developers and designers. Education/Experience Requirements: Relevant degree in Computer Science, Engineering, Cybersecurity, or equivalent experience. Nice to Have Certs CISSP, CCSP, Azure Security Engineer (AZ-500), GIAC (GWEB/GWAPT/GXPN), OSCP. Azure AI Engineer (AI-102), Azure Solutions Architect (AZ-305), AWS Security Specialty. CISA, ISO 27001 Lead Implementer, Responsible AI certifications Employee Benefits Overview: Industry Competitive Compensation Medical and Dental Insurance Paid Time Off/Holidays 401(k) Retirement Plans with Matching Remote Work* Paid Training Employee Referral Program Employee Development Program