Staff Information Security Engineer - AI First
New
R
RithumInformation security
United StatesFull-TimeStaff
Salary$170,000-$220,000 per year
Apply NowOpens the employer's application page
Job Details
- Experience
- 5+ years of security engineering experience
- Required Skills
- PythonTerraform
Requirements
- Have 5+ years of security engineering experience with demonstrated AI/ML security depth, including prompt injection, model supply chain, adversarial inputs, and RAG.
- Use AI tools such as ChatGPT, Copilot, or Claude, and LLM frameworks and APIs such as OpenAI, Anthropic, or LangChain.
- Bring hands-on identity and access expertise across enterprise and cloud identity stacks, including AI systems and non-human identities.
- Have infrastructure- and policy-as-code experience, such as Terraform and OPA/Rego, and scripting proficiency; Python is preferred.
- Demonstrate cloud security expertise, including multi-account governance, preventive guardrails, and policy-as-code.
- Know application security, OWASP Top 10 and OWASP LLM/GenAI Top 10, secure SDLC, and threat-modeling methods such as STRIDE or PASTA.
- Have practical experience building or operating AI agents and integrating security tooling such as SIEM, CSPM, SAST/DAST/SCA.
- Have working knowledge of SOC 2 and/or ISO 27001 control frameworks.
Responsibilities
- Mediate conflicts between security requirements and feasible implementation, propose compensating controls, and track residual risks.
- Implement preventive security controls across cloud and enterprise environments using policy-as-code and infrastructure-as-code.
- Enforce identity and access controls, including access boundaries for AI systems and non-human identities.
- Maintain the InfoSec risk register and translate emerging threats into actionable guidance for engineering teams.
- Support third-party and vendor risk assessments, particularly for vendors processing data through AI pipelines.
- Automate security workflows and build or operate AI-assisted security agents with human approval gates and least-privilege credentials.
- Integrate SIEM, CSPM, DAST/SAST, and vulnerability-scanning tools with LLM layers.
- Define security requirements for AI-powered features, including model access controls, prompt-injection mitigations, output validation, and data-handling boundaries.
- Conduct threat modeling on agentic and LLM-based systems, considering tool misuse, indirect prompt injection, and supply-chain risk.
View Full Description & ApplyYou'll be redirected to the employer's site
