Job Description
Shape the Future of Intelligence. We are pioneering the 2026 landscape of Artificial General Intelligence (AGI). Nexus Horizon Labs is seeking a visionary Senior AI Alignment Engineer to architect the safety and ethical guardrails for our next-generation cognitive systems. If you are passionate about preventing existential risks and ensuring AI benefits all of humanity, this is your opportunity to lead.
Our team is building the foundational models that will power the next century of human advancement. You will work at the intersection of cutting-edge research, complex mathematics, and philosophical inquiry to ensure that superintelligent systems remain beneficial and controllable.
Responsibilities
- Architect Safety Frameworks: Design and implement robust alignment techniques, including Constitutional AI and Red Teaming protocols for large-scale models.
- Model Interpretability: Develop tools to visualize and understand the decision-making processes of complex neural networks.
- Adversarial Defense: Lead the charge in identifying and mitigating vulnerabilities in generative models against prompt injection and data poisoning attacks.
- Ethical Guidelines: Collaborate with ethicists and policy makers to establish industry standards for AI behavior in the 2026 era.
- R&D Leadership: Spearhead research projects focused on value learning and corrigibility.
Qualifications
- Education: PhD in Computer Science, Mathematics, Cognitive Science, or a related field.
- Experience: 5+ years of experience in Machine Learning, specifically in NLP or Reinforcement Learning from Human Feedback (RLHF).
- Technical Skills: Deep expertise in PyTorch, TensorFlow, and transformer architectures.
- Research: Proven track record of publishing in top-tier AI conferences (NeurIPS, ICML, ICLR).
- Problem Solving: Ability to think abstractly about long-term AI safety and complex system dynamics.