Back
Niche adversarial-ML role but metro location and mid-level seniority produce moderate applicant density.
Requires specialized adversarial-ML and LLM red-teaming experience, limiting cross-industry transferability.
Explicit 6+ years plus 3+ years specialized adversarial-ML requirement and specific technical competencies.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Design and execute adversarial ML attack campaigns and lead AI red teaming for LLM, RAG, and agentic AI systems to evaluate and report on security weaknesses.
Own AI-specific threat modeling and produce adversarial-robustness and safety evaluation reports with measurable outputs and mitigation guidance.
Advise cross-functional teams on AI safety and security controls, maintain AI safety testing toolkits, and translate research into reusable evaluation sets and playbooks.
Bachelor's or Master's degree in Computer Science, Information Security, AI/ML, or related quantitative discipline (mandatory).
6+ years total experience in ML, applied AI, security research or closely related discipline, with minimum 3 years in adversarial ML or AI/ML security research.
Hands-on experience with LLM red-teaming covering prompt injection, jailbreaks, and agentic tool misuse campaigns on production or equivalent systems.
Proficient in Python, PyTorch/TensorFlow, Hugging Face Transformers, adversarial ML tools (ART, Foolbox), and threat modeling frameworks (STRIDE, MITRE ATT&CK, MITRE ATLAS).
Senior practitioner with deep domain expertise in adversarial ML and AI red teaming for production-scale AI/ML systems, especially LLMs and generative AI.
Experienced in designing quantitative safety, fairness, hallucination, and calibration metrics and integrating these into development lifecycles.
Able to communicate complex AI safety/security issues effectively across engineering, architecture, compliance, and executive stakeholders while maintaining technical rigor.