Job Description
Are you ready to define the future of humanity? Nexus Future Labs is looking for a visionary AI Safety Engineer 2026 to join our elite team in San Francisco. As we approach the singularity, our mission is to ensure that Artificial General Intelligence (AGI) remains aligned with human values.
In this role, you will be at the forefront of research, developing mathematical frameworks to guarantee the safety and reliability of autonomous systems. If you possess a rigorous technical background and a deep sense of responsibility for the future, we want to hear from you.
Responsibilities
- Architect Safety Frameworks: Design and implement formal verification systems for neural network behaviors to prevent unintended consequences.
- Adversarial Testing: Lead rigorous red-teaming operations to identify vulnerabilities in large language models before deployment.
- Value Alignment: Collaborate with cognitive scientists to map and encode human preferences into algorithmic reward functions.
- Risk Auditing: Conduct continuous audits of our AI pipelines to ensure compliance with evolving global safety standards.
- Research Publication: Author and present groundbreaking papers at top-tier conferences such as NeurIPS and ICML.
Qualifications
- Advanced Degree: PhD or Master’s in Computer Science, Mathematics, Philosophy, or a related quantitative field.
- Experience: 5+ years of experience in AI/ML research, preferably with deep learning or reinforcement learning.
- Technical Skills: Proficiency in Python, Rust, or C++ and familiarity with formal logic and proof assistants (e.g., Coq, Lean).
- Game Theory: Strong understanding of game theory, mechanism design, and multi-agent systems.
- Communication: Excellent ability to communicate complex technical concepts to diverse stakeholders.