Job Description
Shape the Future of Intelligence
Nexus Horizon is seeking a visionary Senior AI Alignment Engineer to lead our efforts in ensuring artificial general intelligence remains beneficial and safe. In this pivotal role, you will work on the precipice of the next technological revolution, designing the critical protocols that govern how advanced AI systems interact with the human world.
Our mission is to bridge the gap between rapid AI innovation and ethical responsibility. You will collaborate with world-class researchers to identify and mitigate potential risks associated with large language models and autonomous agents.
Responsibilities
- Design and implement rigorous safety frameworks for large-scale AI models.
- Conduct adversarial testing and red-teaming exercises to identify system vulnerabilities.
- Develop mathematical proofs and formal verification methods for agent behavior.
- Collaborate with product teams to integrate ethical constraints into deployment pipelines.
- Research and publish findings in top-tier academic conferences and journals.
- Advocate for AI safety best practices within the broader tech community.
Qualifications
- PhD or Master’s degree in Computer Science, Philosophy, or a related field.
- 5+ years of experience in machine learning, NLP, or cognitive science.
- Deep understanding of reinforcement learning and causal inference.
- Proficiency in programming languages such as Python, C++, or Rust.
- Strong track record of translating complex theoretical concepts into practical engineering solutions.
- Exceptional written and verbal communication skills.