"interpretability" Jobs
757 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 757 results
Join Anthropic as a Senior Product Manager to lead the development of Claude Science, an AI workbench for scientific research.
Join Anthropic as a Staff+ Software Engineer to shape the future of AI in scientific research with a focus on reliability and interpretability.
Join Anthropic as a Safeguards Enforcement Analyst to protect against AI misuse in biological contexts.
Drive data-informed decisions across the commercial customer lifecycle as a Data Scientist at Anthropic.
Join Anthropic as a Technical Architect to teach and empower engineering teams using Claude Code and related tools.
Join Anthropic as an Applied AI Architect to help enterprises integrate and deploy Claude into their technology stack.
Join Anthropic as an Applied AI Architect to guide enterprises in integrating AI solutions into their technology stack.
As Data Operations Manager, you'll scale data operations for AI research teams, ensuring high-quality data pipelines and strategic vendor partnerships.
Join Anthropic as a Safeguards Enforcement Analyst to mitigate misuse of AI systems related to conventional weapons.
Join Anthropic as a Director of Technical Revenue Accounting to lead complex revenue recognition and drive financial infrastructure in AI.
Lead consolidated reporting for data center delivery projects at Anthropic, ensuring accurate milestone tracking and data integrity.
Join Anthropic as a Staff Software Engineer to develop AI-powered coding tools that enhance developer productivity and creativity.
Lead the Security Controls Assurance team to define and validate compliance controls for AI systems in a hypergrowth environment.