Security Engineering Intern

AI defensive engineeringsummer cohort $10,000 for ~3 months · 100% remote · flexible hours AI adversarial research and security engineering skunkworksIf you want permissionless research, radical creativity and the freedom to break things the big labs would never let you touch, you'll feel at home here. If you'd rather discover new failure modes than sit in meetings discussing old ones, you'll fit right in.OpenAI has guardrails. Anthropic has constraints. Google has committees.We are the lab built for:investigating adversarial vulnerabilities in LLMsexploring agentic failure modes without restrictionsinventing new classes of jailbreaks, exploits, and failure patternsdesigning the next security layer for autonomous AIrewarding people who discover what others cannotIf you want a safe, structured, corporate internship where you fetch coffee and watch standups, this is not it. If you want to ship real defensive infrastructure that protects production AI agents on day one, you'll fit in immediately.Why this internship is differentMost internships are observational. Ours is operational. From week one you'll own real work that ships to real customers protecting real autonomous agents.no busywork, no shadowing, no "intern projects" that get thrown awayyour code goes into the production SDK that customers deploydirect access to founders, not buried under three layers of managementgrowth based on contribution, not seniorityflexible work — output matters, not hours, work when you do your best thinkingHow we workrapid experimentation — if it works, it shipszero bureaucracy, no waiting for permissionbuild your own tools, exploit frameworks and detection pipelinesuse any language, workflow, or stack you preferasync-first, fully remote, async code reviewsThe roleYou'll work on the defensive side of agent security — building, testing, and hardening the infrastructure that protects autonomous AI systems in production.You will:build detection pipelines across pattern, semantic, and behavioral signalsexpand and harden our red-team test suites against the production SDKship framework adapters that let our security layer plug into LangChain, OpenAI Agents SDK, and other agent runtimesdevelop attack scenarios, payloads and eval datasets that strengthen the productcontribute to dashboard, telemetry and visibility tooling for real-world deploymentsWe are looking forCS, security, or related students (undergrad or grad) who already build things outside of classcomfort with Python and at least one of: TypeScript/React, ML/NLP, or systems-level workcuriosity about LLM internals, agent architectures, and prompt injectionbonus: CTF experience, security research, open source contributions, or your own side projects that broke somethingno specific degree or year required — show us what you've builtDetails$10,000 stipend~3 months, start and end dates flexible100% remote, async-friendlyfull-time preferred (~40 hrs/week), part-time considered for grad studentsUS-based