we are seeking a leading expert to drive security and AI research at the critical intersection of advanced AI Models and core enterprise infrastructure. The researcher will be essential in researching the entire AI lifecycle, from foundational models to sophisticated LLM-based agents and AI applications. You will search for new vulnerabilities, solve complex problems, and develop strategies for both attacking and defending AI environments.
Furthermore, you will be in charge of fostering and spreading technical expertise. You will present your novel work at conferences and author papers and blogs. You will also build AI security tools and solutions.
If youre a curious, creative, technical person with an attackers mindset, strong systemic thinking, and a passion for AI and taking things apart and understanding how they work, we encourage you to apply.
Your Role:
Investigate and analyze the AI systems to find vulnerabilities, security gaps, weaknesses, and design flaws
Follow emerging AI security threats, author blogs about novel research, publish content, and speak at conferences
Build, train and fine-tune AI models to simulate attack vectors and build security mitigation methods
Furthermore, you will be in charge of fostering and spreading technical expertise. You will present your novel work at conferences and author papers and blogs. You will also build AI security tools and solutions.
If youre a curious, creative, technical person with an attackers mindset, strong systemic thinking, and a passion for AI and taking things apart and understanding how they work, we encourage you to apply.
Your Role:
Investigate and analyze the AI systems to find vulnerabilities, security gaps, weaknesses, and design flaws
Follow emerging AI security threats, author blogs about novel research, publish content, and speak at conferences
Build, train and fine-tune AI models to simulate attack vectors and build security mitigation methods
Requirements:
Knowledge of web applications and security mindset
Experience with web attacks, both theoretical and practical
AI/ML Expertise: hands-on experience in training, fine-tuning, and deploying ML models using industry-standard frameworks.
Understanding LLM implementation and what are the current security gaps
Highly motivated, self-driven, curious, responsible, and independent
Proficiency in Python for rapid PoC development, automating adversarial attacks, and building complex simulation environments.
Strong problem-solving skills
Experience with and knowledge of cloud environment architectures
Excellent written and verbal communication skills.
And Ideally:
Prior experience discovering vulnerabilities and publishing research findings
Experience writing blog posts and technical articles
Experience with training ML models, building AI tools or agents
Background in cybersecurity research, vulnerability research, or offensive security
Knowledge of web applications and security mindset
Experience with web attacks, both theoretical and practical
AI/ML Expertise: hands-on experience in training, fine-tuning, and deploying ML models using industry-standard frameworks.
Understanding LLM implementation and what are the current security gaps
Highly motivated, self-driven, curious, responsible, and independent
Proficiency in Python for rapid PoC development, automating adversarial attacks, and building complex simulation environments.
Strong problem-solving skills
Experience with and knowledge of cloud environment architectures
Excellent written and verbal communication skills.
And Ideally:
Prior experience discovering vulnerabilities and publishing research findings
Experience writing blog posts and technical articles
Experience with training ML models, building AI tools or agents
Background in cybersecurity research, vulnerability research, or offensive security
This position is open to all candidates.
