Technical Consultant, AI Security
Work directly with sophisticated engineering and security teams to assess AI systems, identify vulnerabilities, and design practical security architectures.
About the role
You will work with organizations building and deploying real-world AI systems, helping them understand where those systems can fail and what they should do about it. This is a deeply technical consulting role rather than a traditional advisory position. You will assess LLM applications, AI agents, RAG systems, model integrations, tool-calling workflows, and surrounding infrastructure. You will combine application security, cloud security, AI security, and adversarial testing techniques to identify realistic attack paths and help customers prioritize remediation. The strongest candidates will be comfortable moving between a customer's architecture diagram, source code, model behavior, threat model, and executive-level security requirements.
Responsibilities
- Lead technical AI security assessments for customers deploying LLMs, AI agents, RAG systems, and other AI applications.
- Review AI architectures, application code, model integrations, APIs, tool permissions, data flows, and trust boundaries.
- Design and execute adversarial tests including prompt injection, jailbreaks, data exfiltration, tool abuse, privilege escalation, and indirect attacks.
- Develop customer-specific threat models and attack scenarios.
- Produce clear technical reports containing findings, evidence, risk assessments, and practical remediation guidance.
- Work directly with engineering, security, ML, and platform teams to validate findings and develop mitigations.
- Help customers establish repeatable AI security testing and evaluation programs.
- Support technical implementations, pilots, proof-of-concepts, and production deployments.
- Translate complex AI security problems into concise recommendations for technical and executive stakeholders.
- Contribute reusable assessment methodologies, tooling, playbooks, and internal research.
Requirements
- 5+ years of experience in cybersecurity, application security, cloud security, software engineering, ML engineering, or a comparable technical discipline.
- Hands-on experience assessing or securing production software systems.
- Strong understanding of LLM application architectures, APIs, RAG, vector databases, agent frameworks, and tool calling.
- Experience with offensive security, penetration testing, red teaming, application security, or AI security assessments.
- Strong Python and general software engineering skills.
- Ability to understand unfamiliar architectures and codebases quickly.
- Experience communicating technical findings directly to senior engineers, security leaders, and customers.
- Strong written communication and ability to produce high-quality technical reports.
- Ability to travel occasionally for customer engagements if required.