Job Description
Are you ready to define the ethical boundaries of artificial general intelligence? At Synthetix AI, we are preparing for the pivotal year of 2026. As our Lead AI Alignment Strategist, you will be responsible for ensuring that our cutting-edge AGI systems remain safe, beneficial, and aligned with human values. Join us in shaping the future of technology that will define the next decade.
Why join us? We are backed by top-tier VCs and are on a mission to build AI that serves humanity. You will work in a dynamic environment where your expertise directly impacts the trajectory of global AI development.
Responsibilities
- Design and implement safety frameworks for pre-AGI and AGI models.
- Conduct adversarial testing and bias audits on proprietary algorithms.
- Collaborate with policy makers to draft industry standards for 2026.
- Lead research initiatives in interpretability and value learning.
- Develop long-term ethical roadmaps for autonomous systems.
Qualifications
- PhD in Computer Science, Philosophy, or a related field.
- 5+ years of experience in AI safety, machine learning ethics, or formal verification.
- Deep understanding of reinforcement learning and causal inference.
- Proven ability to communicate complex technical concepts to non-technical stakeholders.
- Experience with open-source AI safety toolkits (e.g., MARTA, GYM).