Remote | Member of Technical Staff, Vulnerability Researcher — $240,000–$400,000/year at 24-MAG in New York, New York, United States

Job description

• We are sharing a full-time opportunity for an experienced Vulnerability Researcher with deep expertise in offensive security, red teaming, multi-cloud exploitation, application security, reverse engineering, exploit development, and emerging AI/LLM security.
• The role focuses on advanced security research across cloud infrastructure, production services, developer platforms, AI systems, identity architectures, and software supply chains. The successful candidate will identify novel attack paths, build proof-of-concept tooling, validate remediation efforts, and work closely with engineering teams to strengthen secure-by-design practices.

Responsibilities

• Offensive Security & Vulnerability Research
• Conduct advanced research across cloud infrastructure, production services, internal tooling, applications, APIs, and AI platforms
• Identify architectural weaknesses, vulnerability classes, privilege-escalation paths, and lateral-movement risks
• Perform code auditing, reverse engineering, exploit research, and proof-of-concept development
• Design realistic adversary simulations and advanced red-team scenarios
• Document findings clearly for engineering and security stakeholders
• Cloud, Application & Supply Chain Security
• Assess AWS and GCP environments, including IAM, networking, Kubernetes, containers, and cloud control planes
• Evaluate authentication, authorisation, APIs, proprietary applications, and service interactions
• Review CI/CD systems, infrastructure-as-code, developer workflows, and software supply-chain risks
• Analyse insider-threat and distributed-system attack scenarios
• Validate security controls across complex production environments
• AI/LLM Security & Offensive Tooling
• Research security risks affecting LLMs, AI agents, RAG systems, and tool-enabled workflows
• Evaluate prompt injection, indirect attacks, tool abuse, and autonomous or orchestrated AI systems
• Build custom security tooling, automation, fuzzing utilities, or analysis frameworks
• Develop reproducible proof-of-concept implementations for validated vulnerabilities
• Investigate emerging attack surfaces and novel vulnerability classes
• Remediation & Security Engineering
• Collaborate with infrastructure, product, AI, and security engineering teams on remediation
• Verify that fixes address underlying attack paths and identify residual risk
• Support secure-by-design architecture and development practices
• Produce technical vulnerability reports and document attack methodologies
• Contribute research insights to long-term security strategy

Requirements

• Proven experience in offensive security, vulnerability research, red teaming, or exploit development
• Deep understanding of AWS and GCP security
• Strong knowledge of IAM, cloud networking, Kubernetes, containers, APIs, and identity systems
• Strong application-security, code-auditing, and reverse-engineering experience
• Familiarity with CI/CD and software supply-chain security
• Proficiency in Python, Go, Rust, C/C++, or comparable security-research languages
• Strong knowledge of operating-system internals, networking, and authentication protocols
• Ability to investigate ambiguous technical problems independently and develop novel research approaches
• Excellent written technical communication skills
• Experience with AI/LLM security, agentic systems, prompt injection, tool abuse, or RAG security is highly valuable
• Zero-day discovery, exploit development, published CVEs, security research, bug-bounty work, or open-source tooling is advantageous
• Experience with fuzzing, symbolic execution, binary analysis, macOS internals, endpoint security, virtualisation, or hardware-backed security is beneficial

Skills

Required

• Offensive security
• Vulnerability research
• Red teaming
• Exploit development
• AWS security
• GCP security
• IAM
• Cloud networking
• Kubernetes
• Containers
• APIs
• Identity systems

Preferred

• AI/LLM security
• Agentic systems
• Prompt injection
• Tool abuse
• RAG security
• Zero-day discovery
• Published CVEs
• Bug-bounty work