"interpretability" Jobs
12029 open tech roles matching “interpretability”, taken straight from company career pages — not reposted from other job boards. Every listing is re-checked daily and closed roles are removed.
Showing 20 of 12029 results
Join Anthropic as a Staff Software Engineer to drive reinforcement learning efforts and design systems for coding capabilities.
Join Anthropic as a Performance Engineer to optimize AI inference systems for throughput, latency, reliability, and correctness.
Join Anthropic as a Safeguards Analyst to build enforcement workflows for AI systems against misuse and ensure user safety.
Build evaluation infrastructure for AI safety systems at Anthropic, focusing on real-world misuse detection.
Lead the architecture and technical direction of agentic AI systems at Inflection AI, building production AI agents.
Join Anthropic as a Research Scientist focusing on measuring and understanding recursive self-improvement in AI systems.