Security Analyst

Arrow•Denver, CO

3d•Hybrid

About The Position

AI & LLM Security: Evaluate and assess the security posture of large language model (LLM) deployments, including prompt injection, model inversion, and data leakage risks. Support threat modeling exercises for AI-powered applications and pipelines. Assist in developing and enforcing secure LLM integration standards across business units. Research emerging attack vectors targeting foundation models and generative AI systems. Agentic AI Security: Help design security guardrails for autonomous AI agents, including privilege boundaries, tool-use controls, and output validation. Contribute to the development of policies and frameworks governing agentic AI behavior in production environments. Monitor and audit AI agent activity for anomalous or potentially harmful actions. Collaborate with AI engineering teams to integrate security checkpoints into agent workflows. Generic Security Operations: Participate in security reviews, vulnerability assessments, and risk evaluations of new AI and enterprise technology initiatives. Stay current on AI security research, CVEs, and industry standards (OWASP, NIST AI RMF, MITRE ATLAS).

Requirements

Typically requires a 4-year degree and 1–2 years of experience; or a 2-year degree and equivalent related experience; or equivalent work experience.
Demonstrated knowledge of large language model (LLM) architectures and how they function, including transformer-based models and prompt engineering concepts
Strong analytical and communication skills — able to convey technical security concepts clearly to both technical and non-technical stakeholders
Genuine curiosity about AI systems and a proactive mindset toward identifying and mitigating risk

Responsibilities

Evaluate and assess the security posture of large language model (LLM) deployments, including prompt injection, model inversion, and data leakage risks
Support threat modeling exercises for AI-powered applications and pipelines
Assist in developing and enforcing secure LLM integration standards across business units
Research emerging attack vectors targeting foundation models and generative AI systems
Help design security guardrails for autonomous AI agents, including privilege boundaries, tool-use controls, and output validation
Contribute to the development of policies and frameworks governing agentic AI behavior in production environments
Monitor and audit AI agent activity for anomalous or potentially harmful actions
Collaborate with AI engineering teams to integrate security checkpoints into agent workflows
Participate in security reviews, vulnerability assessments, and risk evaluations of new AI and enterprise technology initiatives
Stay current on AI security research, CVEs, and industry standards (OWASP, NIST AI RMF, MITRE ATLAS)

Benefits

Medical, Dental, Vision Insurance
401k, With Matching Contributions
Short-Term/Long-Term Disability Insurance
Health Savings Account (HSA)/Health Reimbursement Account (HRA) Options
Paid Time Off (including sick, holiday, vacation, etc.)
Tuition Reimbursement
Growth Opportunities
Discounted RTD Passes, with convenient office location off RTD Light Rail (Dry Creek Exit)
On-site Café with Catering Option for Busy Lifestyles
24/7/365 On-site Gym and Lockers, Free for Use to All Employees!
Bike Racks