AI Prompt Engineer - Raleigh, Nc

About the role

An enterprise cybersecurity group in Raleigh is seeking an AI Prompt Engineer to help expand an emerging security program centered around generative AI. The organization is evaluating advanced AI models from a security perspective and developing new ways to use generative models as part of automated security assessment, application testing, and vulnerability research. This engineer will create sophisticated prompt-based testing workflows designed to make AI models perform targeted cyber analysis.

Responsibilities

• Engineer reusable prompt workflows that support AI-assisted security assessments
• Create testing scenarios that push models to investigate applications, infrastructure, and potential attack surfaces
• Develop prompting approaches for static and dynamic application-security analysis
• Evaluate network, port, perimeter, and certificate-related security scenarios through GenAI workflows
• Run experiments against different model providers and compare model behavior and effectiveness
• Continuously adjust instructions, context, and harness logic based on testing results
• Coordinate with data engineers so security output can be normalized, persisted, and analyzed downstream
• Share actionable AI-discovered issues with threat-hunting and security-response teams

Requirements

• Hands-on background designing sophisticated prompt strategies for generative AI
• Practical cybersecurity knowledge, including attack surfaces, vulnerabilities, malicious behavior, and network traffic concepts
• Software engineering or application development experience in languages such as Python, Go, C#, .NET, or similar
• Ability to construct multi-step or context-rich LLM workflows rather than simple single prompts
• Familiarity with one or more modern generative AI/model platforms
• Experience storing, querying, or manipulating data using PostgreSQL, Elasticsearch, Cloud SQL, or related databases
• Strong ability to explain previous AI projects, experimentation methods, and technical design decisions

Qualifications

• Exposure to application security and automated code-security testing
• Background in offensive security, penetration testing, or vulnerability research
• Familiarity with containerized or cloud-hosted applications
• Experience with GKE or Kubernetes
• Previous work evaluating the behavior or security of large language models
• Experience operating in a research-oriented engineering environment

Benefits

• Medical Insurance
• Dental Benefits
• Vision Benefits
• Paid Time Off (PTO)
• 401(k)

Applicants must be currently authorized to work in the US on a full-time basis now and in the future.