Anthropic

Offensive Security Research Engineer, Safeguards

Anthropic

Apply
3 days ago
San Francisco, CA, USA
Mid Level / Senior
H1B Sponsor

Base Salary

$320k - $405k/yr

Responsibilities

  • Triage any vulnerabilities discovered and assist the external community in remediation.
  • Write scaffolds to automate traditional attack techniques for defensive problem selection.
  • Research potential misuse of LLMs to identify and exploit vulnerabilities at scale.
  • Develop defensive strategies to mitigate adversarial misuse of models.
  • Collaborate with a senior team to implement a forward-looking security plan.

Requirements

  • 3+ years of experience in pentesting, vulnerability research, or offensive security.
  • Senior-level knowledge in areas such as reverse engineering, network security, or exploitation.
  • Demonstrated desire to produce high-quality outputs through hands-on work.
  • Software engineering experience is required.
  • Proven ability to lead cross-functional security initiatives.

Benefits

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

Categories

AI & MLSecurity