Staff + Software Security Engineer, Labs na Anthropic

San Francisco, CA, New York City, NY, Seattle, WA

Candidatar-se
Ver mais vagas na Anthropic

Frontier AI’s Security Labs seeks a generalist software engineer with deep expertise in firmware/hardware security, applied cryptography, OS/hypervisor internals, formal methods, reverse engineering, or high‑assurance systems. The role involves owning high‑risk, high‑value research projects that run on a rapid, experimental cadence, building prototypes, testing them against real workloads, and translating findings into actionable architecture and policy. The team operates in a scrappy, ambitious environment, accepting that many experiments will not succeed but learning valuable insights for AI safety and security.

Requirements

Skills

  • firmware or hardware security
  • applied cryptography
  • OS / kernel / hypervisor internals
  • formal methods and verification
  • reverse engineering and exploit development
  • high-assurance / cross-domain systems
  • built and shipped projects under own direction
  • track record of choosing problems and seeing them through
  • ability to jump between domains and layers of the stack
  • experience running prototypes or experiments focused on hard questions
  • strong written communication skills

Responsibilities

  • Own Security Labs projects end to end: scope the bet, build the prototype, run against real workloads, and bring to hand‑off or documented exit
  • Stand up novel security infrastructure fast (isolated clusters, attestation chains, hypervisor and runtime work, verification tooling) optimized for learnings
  • Find receiving teams early, bring them along while building, and hand them deliverables they can own
  • Work embedded with research and infrastructure teams (Pretraining, RL, Inference, Compute) to test workflow resilience and document gaps
  • Turn experimental results into short writeups that shape Anthropic’s long‑term security architecture and contingency plans
  • Help pick the next round of bets and influence the industry toward better security

Technologies

cryptographic verificationzero‑knowledge proofsattestation chainshypervisormicroVMML kernelformally verified pipelinesoftware engineering tools

Compartilhar vaga

Descubra se seu currículo está pronto para esta vaga

Veja como nossa IA pode otimizar seu currículo e aumentar suas chances de conseguir esta posição.