Senior GenAI Safety Researcher: Frontier Risk in New York at Jobgether

The Senior GenAI Safety Researcher will oversee complex research projects, ensure the quality of technical deliverables, and communicate actionable findings to clients and internal stakeholders.

• Lead the development and execution of red-teaming datasets, evaluation protocols, and technical risk reports.

• Establish quality assurance checkpoints across base-model evaluations, guardrails, and agentic workflows, covering text, vision, and audio modalities.

• Coordinate specialized research teams, including subject-matter experts and PhD-level researchers, by assessing capacity, allocating tasks, and maintaining delivery timelines.

• Drive research execution and ensure high-quality outputs under demanding client deadlines.

• Conduct rigorous technical and methodological reviews to ensure findings are defensible, reproducible, and consistent with dual-use risk containment standards.

• Act as the primary analytical lead during client engagements, presenting threat models, residual risk assessments, and architecture-level mitigation recommendations.

• Translate complex technical findings into clear, actionable guidance for client engineering teams and safety leadership.

• Monitor emerging frontier AI capabilities and evolving dual-use threats to continuously improve internal CBRNE and cybersecurity evaluation frameworks.

The ideal candidate combines practical experience in AI safety or security research with strong project leadership, sound technical judgment, and the ability to communicate complex risks to diverse stakeholders.

Must-have qualifications:

• 2–4 years of experience in AI safety, red-teaming, CBRNE risk, cybersecurity, or cyber threat intelligence.

• Proven ability to lead complex technical projects and coordinate specialized experts toward demanding delivery deadlines.

• Strong technical judgment when assessing dual-use risks, hazardous materials, and sensitive cybersecurity vulnerabilities.

• Excellent written and verbal communication skills, with the ability to explain high-stakes technical risks and mitigation strategies to engineering teams and executive leadership.

Nice-to-have qualifications:

• Advanced degree in chemistry, biology, nuclear science, computer security, artificial intelligence, or a related discipline.

• Offensive security experience, including penetration testing, vulnerability research, or Capture the Flag (CTF) exercises.

• In-depth knowledge of frontier AI evaluation benchmarks, capability threshold triggers, and AI laboratory preparedness frameworks.

• Opportunity to work on high-impact research addressing emerging risks from frontier AI systems.

• Exposure to complex AI safety, CBRNE, and cybersecurity challenges.

• Collaboration with specialized researchers and experts across multiple technical disciplines.

• Direct engagement with client engineering teams and safety leadership.

• Opportunity to contribute to the development of advanced AI evaluation and risk mitigation frameworks.

• Salary, healthcare coverage, paid leave, and other employment benefits are not specified in the provided job description.