Software Engineer — AI Safeguards & Oversight

SignalAI; New York (NY); Hybrid; USD 320,000 - 485,000; Full time

Job summary

Anthropic is seeking software engineers to build safety and oversight mechanisms for AI systems on the Safeguards team. You will monitor models, prevent misuse, and ensure user well-being by detecting unwanted behaviors and enforcing policies.

Multiple Safeguards teams hire with flexible placement after interviews. You will work across sandboxed architectures and data pipelines to maintain safety, trust, and scale across Claude-based systems.

Qualifications

• Bachelor's degree in Computer Science, Software Engineering or comparable experience.
• Proficiency in Python and TypeScript.
• Ability to work across the stack.
• Strong communication skills and ability to explain complex technical concepts to non-technical stakeholders.

Responsibilities

• Develop monitoring systems to detect unwanted behaviors from API partners and surface actions to analysts.
• Build abuse detection mechanisms and infrastructure.
• Surface abuse patterns to research teams to harden models at training.
• Build reliable defenses for real-time safety improvements at scale.

Skills

Python

TypeScript

Distributed systems

API design

Communication

Education

Bachelor's degree in Computer Science or related field

Job description

Anthropic is seeking software engineers to build safety and oversight mechanisms for AI systems on the Safeguards team. You will monitor models, prevent misuse, and ensure user well-being by detecting unwanted behaviors and enforcing policies.

Multiple Safeguards teams hire with flexible placement after interviews. You will work across sandboxed architectures and data pipelines to maintain safety, trust, and scale across Claude-based systems.