Anthropic

Research Engineer, Frontier Red Team (Autonomy)

Anthropic

Apply
about 1 month ago
San Francisco, CA, USA
Mid Level / Senior
H1B Sponsor

Base Salary

$350k - $850k/yr

Responsibilities

  • Design and build autonomous AI systems that can operate across diverse environments.
  • Create evaluations and training environments to shape agent behavior.
  • Develop defensive agents to detect and disrupt adversarial AI systems.
  • Interface AI with hardware platforms to assess cyberphysical risks.
  • Translate technical findings into demonstrations for policymakers and the public.
  • Collaborate with external experts in cybersecurity and AI safety.

Requirements

  • Strong software engineering skills, particularly in Python.
  • Experience with LLM-based agents or autonomous systems.
  • Ability to solve ambiguously scoped, high-stakes problems.
  • Experience in designing and running experiments quickly.
  • Strong collaboration skills, including pair programming.
  • A deep commitment to AI safety and its real-world impact.
  • Ability to manage entire problems end-to-end.

Benefits

  • Competitive compensation and benefits.
  • Optional equity donation matching.
  • Generous vacation and parental leave.
  • Flexible working hours.
  • Collaborative office space.

Tech Stack

PythonRobot Framework

Categories

AI & MLEmbeddedSecurity