Research Scientist at FAR.AI

This role is ideal for mid-to-senior level researchers with a PhD or equivalent experience in Machine Learning who are passionate about AI safety. It is a particularly good fit for "unconventional" candidates—those who have their own research agendas or a strong desire to transition from general ML into safety-specific areas like red-teaming, mechanistic interpretability, or adversarial robustness. The position offers rare flexibility for a research role, including fully remote options (US and International) or an in-person environment in Berkeley (and soon Singapore). Compensation is competitive for the non-profit sector ($120k–$190k), and the culture emphasizes "research freedom" that bridges the gap between slow-moving academia and product-focused corporate labs. You’ll benefit from high-end GPU clusters and opportunities to collaborate directly with national AI safety institutes and frontier model labs. **You might be a good fit if you...** * Have a strong track record of publishing at top-tier conferences like NeurIPS, ICLR, or ICML. * Want to move beyond theory and build "minimum viable prototypes" that influence AI policy and corporate deployment. * Are proficient in Python and comfortable with a rigorous technical hiring process, including a 72-minute coding test and a paid work trial. * Are excited about developing novel attacks or "lie detectors" for LLMs.