[Hiring] AI Infra Security Engineer @Binance

Role Description

As the digital-asset industry continues to evolve, so does the risk landscape across the infrastructure. To stay ahead, Binance Infra Team is investing heavily in AI-driven abnormal detection, incident management and system pentest, so that we can proactively identify and address potential vulnerabilities and keep our platform secure.

You will join Binance Infra Team to secure our cloud estate: large-scale, multi-account footprints across AWS, GCP, and Alibaba Cloud, plus the CI/CD and artifact pipelines that feed them.

Our scope is production cloud infrastructure, not corporate IT or employee devices. We operate large-scale host and runtime activity monitoring across the fleet, and we prefer open-source, cloud-native solutions.

Increasingly, that work is done with LLM agents: a fleet of agents that carries out SOC analysis and pentesting, operating tooling through well-defined tool interfaces inside a harness we build and secure ourselves.

What You’ll Do

• AI-Powered Penetration Testing:
  • Leverage LLM-driven agents to automate reconnaissance, attack path discovery, proof-of-concept (PoC) generation, and false-positive triage across cloud infrastructure, internal applications, and APIs.
  • Benchmark AI-driven findings against human-led assessments, measure detection accuracy and coverage, and continuously optimize capabilities based on validated real-world results.
• AI-Driven Infrastructure Security:
  • Leverage AI to identify critical CVEs affecting our systems and generate actionable remediation recommendations.
  • Use AI to detect system misconfigurations, identify potential security risks, and trigger alerts.
  • Automate the analysis of logs across diverse systems using AI to identify suspicious activities, detect potential threats, and generate actionable alerts.
• AI Systems Security:
  • Leverage AI to identify security vulnerabilities in LLM applications, AI agents, and MCP servers, including prompt injection, jailbreaks, tool misuse, data exfiltration, and privilege escalation.
  • Translate red-team findings into actionable security controls, including least-privilege IAM and tool permissions, sandboxing, input/output filtering, human-in-the-loop approvals, and comprehensive audit logging.
  • Integrate AI security regression testing into CI pipelines to continuously validate new models, prompts, and tools against emerging attack scenarios before production deployment.

Qualifications

• Majoring in Computer Science, Artificial Intelligence, Machine Learning, Statistics, Mathematics or a closely related field.
• Knowledge of at least one cloud (AWS, GCP, or Azure), and you have deployed something on it yourself.
• Relevant hands-on experience in using LLMs and coding agents in your projects, and have applied them to at least one security task (e.g., code review, recon, or analyzing a vulnerability).
• Relevant hands-on experience in AI/ML, prompt injection or jailbreaks against LLM applications, through prior internships, work experience, research projects or competitions.
• Strong passion for AI and a solid understanding of modern AI technologies such as LLMs, agents and deep learning, including their strengths and limitations.
• Hands-on experience applying AI to real problems, and an AI-native way of working that makes active use of AI tools in daily research and development.
• Excellent problem-solving skills, analytical rigour and the ability to work on ambiguous, adversarial problems where attackers keep adapting.
• Strong communication and documentation skills. Able to explain technical findings clearly to both technical and non-technical stakeholders.
• Able to commit to an internship of at least 6 months preferred, with consistent weekly hours.

Nice to Haves

• Exposure to security fundamentals: secrets management, SBOM / software supply chain, vulnerability scanning, etc.
• Currently enrolled in a Master's or PhD programme at a QS World University Rankings Top 50 university.
• Cloud infrastructure security experience: linux and container security, network security, HIDS, WAF, IAM, etc.
• CVEs, bug bounty awards, or strong CTF results.
• Hands-on experience on building AI-driven tooling for security work, such as recon, vulnerability discovery, or triage.
• Familiarity with the OWASP Top 10 for LLM Applications, the OWASP Top 10 for Agentic Applications, and MITRE ATLAS.

Benefits

• Shape the future of finance.
• Collaborate with world-class talent in a user-centric global organization with a flat structure.
• Tackle challenging projects in a fast-paced and innovative environment with autonomy.
• Thrive in a results-driven workplace with opportunities for career growth and continuous learning.
• Competitive salary and company benefits.
• Remote-first, work-from-home arrangement (may vary depending on the nature of the role and team).