Senior GenAI Safety Researcher: Frontier Risk
New
J
JobgetherAI safety
Based in the United StatesFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 2–4 years of experience in AI safety, red-teaming, CBRNE risk, cybersecurity, or cyber threat intelligence.
- Required Skills
- Cybersecurity
Requirements
- Have 2–4 years of experience in AI safety, red-teaming, CBRNE risk, cybersecurity, or cyber threat intelligence.
- Demonstrate the ability to lead complex technical projects and coordinate specialized experts toward demanding deadlines.
- Apply strong technical judgment to dual-use risks, hazardous materials, and sensitive cybersecurity vulnerabilities.
- Communicate high-stakes technical risks and mitigation strategies in writing and verbally to engineering teams and executive leadership.
- Advanced degree in chemistry, biology, nuclear science, computer security, artificial intelligence, or a related discipline is nice to have.
- Offensive security experience, including penetration testing, vulnerability research, or Capture the Flag (CTF) exercises, is nice to have.
- Knowledge of frontier AI evaluation benchmarks, capability threshold triggers, and AI laboratory preparedness frameworks is nice to have.
Responsibilities
- Lead the development and execution of red-teaming datasets, evaluation protocols, and technical risk reports.
- Establish quality assurance checkpoints for base-model evaluations, guardrails, and agentic workflows across text, vision, and audio modalities.
- Coordinate subject-matter experts and PhD-level researchers by assessing capacity, allocating tasks, and maintaining delivery timelines.
- Drive research execution and deliver high-quality outputs under client deadlines.
- Review technical methods and findings for defensibility, reproducibility, and consistency with dual-use risk containment standards.
- Lead client analysis by presenting threat models, residual risk assessments, and architecture-level mitigation recommendations.
- Translate technical findings into actionable guidance for client engineering teams and safety leadership.
- Monitor frontier AI capabilities and dual-use threats to improve CBRNE and cybersecurity evaluation frameworks.
View Full Description & ApplyYou'll be redirected to the employer's site
