Job Description
Are you ready to shape the ethical boundaries of artificial general intelligence? Neural Horizon Labs is pioneering the frontier of Next-Generation AI Safety, and we are seeking a visionary Senior AI Alignment Architect to join our elite team.
In this pivotal role, you will bridge the gap between complex machine learning algorithms and philosophical frameworks to ensure that superintelligent systems operate in alignment with human values. We are building the infrastructure for the year 2026 and beyond, and your expertise will be the cornerstone of our mission.
Why Join Us?
Work on the most critical problems in AI safety. Collaborate with world-class researchers and engineers. Competitive equity and benefits package.
Responsibilities
- Design and implement robust reward models to steer large language models toward desired outcomes.
- Conduct rigorous red-teaming and adversarial testing to identify and mitigate alignment risks.
- Collaborate with cognitive scientists and ethicists to define value alignment principles.
- Develop interpretable AI frameworks that make black-box models transparent and auditable.
- Lead research initiatives in causal inference and counterfactual reasoning for AI agents.
- Oversee the deployment of safety guardrails in production environments.
Qualifications
- PhD or Master’s degree in Computer Science, Mathematics, Philosophy, or a related technical field.
- 5+ years of experience in machine learning, specifically in NLP and deep learning architectures.
- Proven track record of publishing in top-tier AI conferences (NeurIPS, ICML, ICLR).
- Deep understanding of reinforcement learning from human feedback (RLHF) and Constitutional AI.
- Strong ability to communicate complex technical concepts to non-technical stakeholders.
- Experience with safety-critical systems and risk assessment methodologies.