SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 320,000 - 485,000 / annual
Anthropic's Security Labs team runs a portfolio of high-risk, high-expected-value security research projects focused on frontier AI systems. This is intentionally scrappy and ambitious work: projects run on the order of weeks rather than quarters, with a meaningful fraction expected not to land. Each project is either handed off to an Anthropic team for production ownership or wound down with documented learnings.
You will own Security Labs projects end-to-end: scoping the bet, building prototypes, running them against real workloads, and bringing them to either handoff or documented exit. You'll stand up novel security infrastructure fast—isolated clusters, attestation chains, hypervisor and runtime work, verification tooling—optimizing for what you learn rather than permanence. You'll find receiving teams early, bring them along while building, and hand them something they actually want to own. You'll work embedded with research and infrastructure teams (Pretraining, RL, Inference, Compute) to test whether their workflows survive your proposals and document precisely where they don't. You'll turn experimental results into short writeups that shape Anthropic's long-term security architecture and into costed contingency plans executable on short notice. You'll help pick the next round of bets and influence the industry to improve.
Current project areas include: standing up a prototype high-assurance research cluster with extreme isolation and physical security; provable inference via cryptographic verification (zero-knowledge proofs, attestation chains); hypervisor-isolated microVM workload isolation across the fleet; compiling ML kernels through formally verified pipelines with machine-checked proofs of equivalence; regenerating clusters with TTL-based automation to expire attacker persistence; and using Claude itself to drive security work end-to-end (threat modeling, service rewriting, hardware validation).
The team is looking for generalists with rare depth: you're a strong software engineer as a baseline, and you've gone deep in at least one area most engineers don't touch—firmware or hardware security, applied cryptography, OS/kernel/hypervisor internals, formal methods, reverse engineering, or high-assurance and cross-domain systems. You've built things under your own direction, you're comfortable jumping layers when the problem demands it, and you'd rather take a swing at something that might not work than ship the safe incremental thing.
**Requirements:**
- Genuinely care about where AI is heading and want to work on the security problems that determine whether it goes well
- Have real depth in at least one area most software engineers don't touch (e.g., firmware or hardware security, applied cryptography, OS/kernel/hypervisor internals, formal methods and verification, reverse engineering and exploit development, or high-assurance/cross-domain systems)
- Have built and shipped things under your own direction (founded a company or research group, maintained an open-source project others depend on, or shipped research that changed how people in your field work)
- Have a track record of choosing the problem yourself and seeing it through, rather than only executing a plan someone else handed you
- Be comfortable jumping between domains and layers of the stack when the problem calls for it, and have actually done so
- Have run prototypes or experiments where the goal was answering a hard question rather than shipping a permanent system, including ones that didn't pan out
- Write clearly enough to turn weeks of work into a couple of pages someone can act on
- Change your mind when the evidence says to, and be fine being the least-expert person in a room full of specialists
- Care about defense (offensive background is valuable, but you want to spend your time now making systems hold up)
- Be a strong programmer (Python plus at least one of Rust, Go, or C/C++) and can stand up real infrastructure without that being the interesting part of your week
- Bachelor's degree or equivalent combination of education, training, and/or experience in a field relevant to the role
**Preferred qualifications:**
- Experience inside airgapped or high-side environments (classified networks, cross-domain solutions, ICS/SCADA, financial trading infrastructure) and operational realities of working in them
- Background in offensive security, red teaming, or vulnerability research with calibrated intuitions for which threats actually matter
- Familiarity with ML infrastructure (training pipelines, distributed schedulers, inference serving, accelerator hardware) sufficient for grounded conversations with researchers
- History of working in environments built around rapid iteration rather than rigid change control (startups, applied research groups, independent consulting, small security shops)
