S
Senior Offensive AI Security Researcher
Not specifiedFull-timeSecurity ResearchEnterprise Software
An enterprise AI and CRM company is seeking a senior researcher to lead offensive security research across its AI ecosystem. The role focuses on discovering emerging vulnerabilities, developing attack techniques, informing AI architecture and threat models, and communicating high-impact risks to##?
Responsibilities
- Lead risk-based adversarial research across AI systems to identify novel threats before exploitation
- Develop and operationalize attack techniques for indirect prompt injection, tool abuse, excessive agency, RAG poisoning, data extraction, and model or data supply-chain compromise
- Guide AI architecture decisions, internal threat models, corporate governance, and generative AI security standards
- Publish internal and external threat intelligence, vulnerability analyses, and security research
Requirements
- At least 5 years of experience in offensive security, vulnerability research, penetration testing, application security, or security engineering
- At least 2 years of hands-on experience auditing, breaking, or researching machine learning and AI systems
- Deep expertise in large language model attack surfaces and frameworks such as OWASP Top 10 for LLMs and MITRE ATLAS
- Strong understanding of retrieval-augmented generation, autonomous agent workflows, model context protocols, and AI pipelines
- High proficiency in Python for exploit proof-of-concept development, data analysis, and technical evaluation
- Experience leading complex security initiatives and communicating high-stakes technical risks to research engineers and executive leadership
Nice to have
- A master’s or doctoral degree in computer science, machine learning, cybersecurity, or a related field
- A public portfolio of offensive security research, including conference presentations, published papers, CVEs, advisories, or open-source contributions
- Experience auditing AI development ecosystems and tools such as PyTorch, Hugging Face, LangChain, vector databases, or open-weight models
Benefits
- Wellbeing reimbursement
- Generous parental leave
- Adoption assistance
- Fertility benefits