Job Description
Architect the Ethical Future of Intelligence.
Quantum Horizon Labs is pioneering the next generation of Artificial General Intelligence (AGI). We are seeking a visionary Senior AI Alignment Engineer to join our elite Seattle team. In 2026, we are moving beyond simple automation to solving the critical problem of ensuring AI systems act in accordance with human values. If you are passionate about the intersection of cognitive science, advanced mathematics, and deep learning, this is your opportunity to define the operating principles of tomorrow's superintelligence.
Why Join Us?
- Impact at Scale: Your work will directly influence the safety protocols of systems used globally.
- Future-Proof Career: Be at the forefront of the most critical conversation in tech.
- Top-Tier Compensation: Competitive salary and equity package for industry leaders.
Responsibilities
- Develop Constitutional AI Frameworks: Design and implement novel architectures for embedding human values directly into the training loops of large language models.
- Conduct Safety Audits: Perform rigorous adversarial testing and red-teaming exercises to identify potential failure modes in our AI agents.
- Define Alignment Metrics: Create quantifiable benchmarks for measuring the 'helpfulness' and 'harmlessness' of AI outputs in complex, ambiguous scenarios.
- Collaborate with Cognitive Scientists: Partner with researchers to translate psychological theories of intentionality into computational constraints.
- Mentor Junior Researchers: Guide a team of data scientists and ML engineers in best practices for safe model deployment.
- Stay Ahead of the Curve: Monitor global developments in AI safety and regulatory landscapes to ensure our solutions remain compliant and robust.
Qualifications
- Education: Ph.D. or Master's degree in Computer Science, Mathematics, Philosophy (with a focus on Ethics), or a related technical field.
- Technical Mastery: Deep expertise in Python, PyTorch, or TensorFlow, with a proven track record of publishing in top-tier AI conferences (NeurIPS, ICML, ICLR).
- Experience: Minimum 5 years of experience in Natural Language Processing (NLP) or Reinforcement Learning (RL).
- AI Safety: Demonstrated interest or experience in AI safety, interpretability, or value alignment research.
- Problem Solving: Exceptional ability to think abstractly and solve ill-defined, complex problems with incomplete information.
- Communication: Ability to articulate complex technical concepts to both technical and non-technical stakeholders.