AI Security Manager

This is a fully remote position, open to applicants in Brazil.

📋 Description

• Coordinate and prioritize security assessments for applications utilizing LLMs, focusing on scenarios including prompt injection, jailbreaks, data exfiltration, tool misuse, and context manipulation.

• Supervise the execution of test cases on both internal and user-facing agents, ensuring consistency with team-established playbooks.

• Spearhead the creation of test suites and tools, such as Promptfoo or similar, fostering innovation and operational efficiency.

• Oversee the monitoring and analysis of alerts and signals produced by controls like LLM Firewall, guardrails, Anonymizer, and AI Gateway, guaranteeing timely and effective responses.

• Validate and review functional and regression tests on AI Security services and controls, ensuring the quality and security of deliverables.

• Direct the analysis of logs, metrics, and events pertaining to LLM traffic, agents, and internal platforms, identifying patterns and opportunities for enhancement.

• Manage the detection of false positives and negatives, and suggest enhancements to rules, heuristics, and detection policies.

• Review and authorize security assessments for MCPs, skills, and tools utilized by developers or agents.

• Ensure the security of ML artifacts, supply chains, and quality gates within pipelines, advocating for best practices and compliance.

• Document and review technical findings, evidence, FAQs, guides, playbooks, and best practices, ensuring clarity and applicability.

• Foster education and awareness initiatives, CTFs, meetups, applied research, and the consolidation of technical references, enhancing the security culture within the team and throughout the organization.

⛳️ Requirements

• Strong background in information security, software development, infrastructure, or related disciplines.

• In-depth understanding of APIs, HTTP, authentication, authorization, logging, and event analysis.

• Proficient in at least one programming language, ideally Python, Go, or JavaScript/TypeScript.

• Experience with Git, GitLab/GitHub, CI/CD pipelines, and code comprehension.

• Interest and knowledge in Artificial Intelligence, LLMs, agents, Machine Learning, or AI security.

• Capability to transform technical insights into strategies, tests, checklists, or actionable recommendations.

• Exceptional written and verbal communication skills for documenting and presenting tests, findings, evidence, and recommendations.

• Meticulous attention to detail in analyzing logs, permissions, prompts, configurations, and data flows.

• Technical leadership, curiosity, and the ability to adapt continuously based on feedback and learning.

• Responsible management of sensitive data, credentials, internal environments, and security test results.

🏝️ Benefits

• Transform your career with iFood!

• Work at a prominent Brazilian technology company renowned throughout Latin America.

• Connect thousands of restaurants to millions of consumers every day.