"ai interpretability" Jobs
761 open tech roles matching “ai interpretability”, taken straight from company career pages — not reposted from other job boards. Most in demand right now: AI/ML, Python, SQL. Every listing is re-checked daily and closed roles are removed.
Showing 20 of 761 results
Join Anthropic as a Staff+ Software Engineer to build safety mechanisms for AI systems with a focus on data governance and integrity.
Join Anthropic's Inference team to design and maintain distributed systems that serve AI models to millions of users worldwide.
Join Anthropic as a Staff+ Research Engineer to build and maintain the RL Data Platform for reliable AI systems.
Join Anthropic as a Staff Software Engineer to build scalable ML infrastructure for AI safety systems.
Own the technical strategy for config and experimentation infrastructure at Anthropic, enhancing developer productivity in AI systems.
Join Anthropic as a Staff Software Engineer to shape privacy engineering in AI systems at scale.
Own the red-teaming and adversarial evaluation pipeline for Reflection’s models to ensure safety and reliability.
Lead the events strategy at Goodfire, creating high-signal experiences for technical audiences in AI.
Own the quality bar for human evaluations at a fast-scaling AI company transforming legal services.
Join Goodfire as a Forward Deployed Research Scientist to lead research in AI interpretability and computational biology.
Join Anthropic as a Staff+ Software Engineer to build safety and oversight mechanisms for AI systems in a hybrid work environment.
Join Reflection AI as a Forward Deployed Engineer to fine-tune models and work directly with enterprise customers in a dynamic startup environment.
Join Anthropic as a Research Counsel to navigate complex legal questions in AI development and ensure responsible research practices.