Research Engineer - AI Safety at fast-growing AI safety research lab

Join a pioneering team dedicated to ensuring advanced AI systems are developed and deployed safely. This role bridges theoretical AI safety research with practical implementation, building critical infrastructure and conducting cutting-edge experiments on frontier AI models. Make a significant impact on the future of AI alignment, interpretability, and robustness.

Fast-growing AI safety research lab

• Build and maintain robust research infrastructure, including evaluation frameworks and automated testing pipelines for frontier models.
• Design and execute scientific experiments to test hypotheses about AI safety, alignment, interpretability, or robustness.
• Collaborate closely with research scientists, ML engineers, and safety evaluators to address pressing AI challenges.

• 4-6 years of professional experience in software engineering or ML engineering with strong Python proficiency.
• Hands-on experience with modern ML frameworks (PyTorch, JAX) and LLM-based systems, including agent scaffolding.
• Familiarity with AI safety concepts (alignment, interpretability, robustness) and proven ability to develop research infrastructure.

• Make a meaningful impact on the future of AI safety by working with state-of-the-art models and contributing to global research.
• Join a well-funded organization backed by top-tier VCs, focused on critical, cutting-edge AI research.
• Opportunity to bridge theoretical insights with practical implementations, developing crucial infrastructure for AI safety.