Research Engineer - AI Safety at mission-driven AI company

Join a mission-driven AI company as a Research Engineer to bridge theoretical AI safety research with practical implementation. You will build critical infrastructure and conduct cutting-edge experiments on frontier AI models, ensuring advanced AI systems are developed and deployed safely. This role offers a unique opportunity to make a significant impact on the future of AI.

Mission-driven AI research company

• Build and maintain robust research infrastructure, including evaluation frameworks and automated pipelines for frontier models (10B-100B+ parameters).
• 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 translate insights into empirical validation.

• Possesses 4-6 years of professional experience in software engineering, ML engineering, or a related technical role.
• Demonstrates strong proficiency in Python with experience in modern ML frameworks like PyTorch, JAX, or TensorFlow.
• Has hands-on experience with LLM-based systems and familiarity with AI safety concepts and research areas.

• Make a meaningful impact on the future of AI safety by working on pressing challenges in alignment, interpretability, and robustness.
• Collaborate with leading experts and gain early access to unreleased frontier AI models from top-tier labs.
• Bridge the gap between theoretical research and practical application, building critical infrastructure while conducting cutting-edge experiments.