"interpretability" Jobs
758 open tech roles matching “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 758 results
Join Anthropic as a Staff Software Engineer to design APIs and frameworks for reinforcement learning environments in a collaborative AI research team.
Join Anthropic as a Product Manager to lead the development of monetization strategies for AI platforms across various industries.
Lead accounting for Anthropic's compute stack, ensuring financial accuracy and scalability in a rapidly growing environment.
Join Anthropic as a Front End Engineer to build and maintain high-quality web experiences for our marketing team.
Join Goodfire as Chief of Staff to enhance leadership effectiveness in a mission-driven AI research company.
Drive scaling and efficiency programs for Anthropic's API stack while managing cross-org dependencies in a hybrid work environment.
Lead the Influence Operations & Surveillance team to counter misuse of AI systems in a rapidly evolving threat landscape.
Join Anthropic as a Staff+ Site Reliability Engineer to ensure safe AI model launches and automate deployment processes.
Join Anthropic as a Research Engineer to advance AI in life sciences through innovative machine learning techniques.
Join Anthropic as a Staff Software Engineer to enhance deployment infrastructure for AI systems in a collaborative environment.
Lead a research engineering team focused on biological safety evaluations and classifiers in a mission-driven AI organization.
Join Perplexity as a senior data staff member to build AI systems that transform data science workflows.
Join Anthropic as a Product Manager to ensure AI systems are safe and beneficial for users across various platforms.
Join Anthropic as a Data Scientist to build a data-driven culture and enhance AI safety and product strategy.
Join Anthropic's Safeguards team as a Red Team Engineer to enhance the safety of AI systems through adversarial testing.