AI Safety Expert - Red Team
WFA Digital Insight
The demand for AI safety experts has grown significantly, with a 25% increase in job postings over the past year. As companies like mercor invest in AI research, the need for professionals who can identify and mitigate risks has become crucial. With the rise of remote work, digital skills are more valuable than ever. mercor's innovative approach to connecting talent with leading AI research labs makes this role stand out. Before applying, candidates should be prepared to showcase their experience in red teaming, cybersecurity, and socio-technical probing, as well as their ability to work independently in a remote setting.
Job Description
About the Role
As an AI Safety Expert at mercor, you will play a critical role in ensuring the safety and security of AI systems. Your primary responsibility will be to conduct red team testing, identifying potential vulnerabilities and risks in AI models and agents. You will work closely with a team of experts to develop and implement testing frameworks, benchmarks, and playbooks to maintain consistent testing.The role involves working on a wide range of projects, from conversational AI models to socio-technical risk assessments. Your expertise in AI, cybersecurity, and socio-technical probing will be essential in identifying and mitigating potential risks. You will also be responsible for generating high-quality human data, annotating failures, classifying vulnerabilities, and flagging systemic risks.
Mercor's team is composed of experienced professionals who are passionate about AI research and development. As a remote worker, you will be expected to be self-motivated and disciplined, with excellent communication skills to collaborate with colleagues and stakeholders.
What You Will Do
- Conduct red team testing of conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation
- Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
- Apply structure to testing by following taxonomies, benchmarks, and playbooks to maintain consistent testing
- Document reproducibly by producing reports, datasets, and attack cases that customers can act on
- Review AI outputs on sensitive topics like bias, misinformation, or harmful behaviors
- Participate in higher-sensitivity projects, including those related to cybersecurity and socio-technical risk
- Collaborate with cross-functional teams to develop and implement testing frameworks and benchmarks
- Stay up-to-date with the latest developments in AI, cybersecurity, and socio-technical probing
- Identify and mitigate potential risks in AI systems, including those related to bias, fairness, and transparency
What We Are Looking For
- Fluent language skills in English and Assamese
- Prior experience in red teaming, cybersecurity, or socio-technical probing
- Ability to push systems to breaking points with a curious and adversarial mindset
- Structured approach to testing using frameworks or benchmarks
- Strong communication skills to explain risks to technical and non-technical stakeholders
- Adaptability to move across projects and customers
- Experience with Adversarial ML, Cybersecurity, and socio-technical risk
- Skills in creative probing, such as psychology, acting, or writing for unconventional adversarial thinking
- Ability to work independently in a remote setting
Nice to Have
- Experience with AI research and development
- Knowledge of machine learning and deep learning concepts
- Familiarity with programming languages such as Python, Java, or C++
- Experience with cloud-based technologies and platforms
Benefits and Perks
- Competitive hourly rate
- Opportunity to work with a leading AI research company
- Collaborative and dynamic work environment
- Professional development and growth opportunities
- Flexible working hours and remote work arrangement
- Access to cutting-edge technologies and tools
- Recognition and reward for outstanding performance
- Comprehensive benefits package, including health insurance and retirement plan
- Paid time off and holidays
- Remote stipend and equipment allowance
How to Stand Out
- Develop a strong portfolio showcasing your experience in red teaming, cybersecurity, and socio-technical probing.
- Practice your communication skills to explain complex technical concepts to non-technical stakeholders.
- Stay up-to-date with the latest developments in AI, cybersecurity, and socio-technical probing.
- Be prepared to provide specific examples of your experience and skills during the interview process.
- Highlight your ability to work independently in a remote setting and your self-motivation and discipline.
- Research mercor's company culture and values to demonstrate your understanding of their mission and goals.
- Prepare questions to ask during the interview, such as those related to the company's approach to AI safety and security.
This is a remote position listed on WFA Digital, the platform for professionals who work from anywhere. Browse more remote jobs across all categories.