Careers / Anthropic

Open role

Research Engineer, Cybersecurity RL at Anthropic

A mid-level AI Security Engineer role at Anthropic, based in San Francisco, CA | New York City, NY. AI Security Engineers attack and defend LLM applications, agents, and ML systems against prompt injection, data leaks, tool abuse, and model evasion. Interviews test your ability to identify attack vectors in LLM workflows, design secure architectures, and reason through complex threat scenarios involving multi-stage attacks and indirect injection chains.

  • 8 skills
  • 10 interview questions
  • 6 labs

The role

  1. CompanyAnthropic
  2. LocationSan Francisco, CA | New York City,
  3. Listed9 days ago
  4. LevelMid

We are not the employer. You apply through the company careers page.

Your readiness for this role

Sign in to see how ready you are for AI Security Engineer roles, skill by skill, and what to do next. Or look at the full AI Security Engineer career track.

Tailored to this job Premium

The pack on this page fits this kind of role. Premium members also get a version read from this exact advert: what this employer stresses, what it requires, how to pitch yourself, five extra questions written for it, and the five questions from the set most worth practising.

Get Premium to tailor it

Skills this role needs

  • Prompt Injection Attack VectorsDirect attacks on LLM inputs are the most common threat; you need to recognize patterns across direct, indirect, encoding, and jailbreak techniques.
  • LLM Agent Hijacking and Tool AbuseAgents with tool access create new attack surfaces through tool confusion, output injection, and privilege escalation that go beyond chat-only models.
  • Data Exfiltration and Leakage DetectionSystem prompts, training data, and user conversations are high-value targets; you must spot extraction attacks and design defenses.
  • Secure System Prompt DesignHardening prompts against extraction and instruction conflict requires deep understanding of attention, context windows, and adversarial phrasing.
  • RAG and Knowledge Base PoisoningRetrieval-augmented systems introduce attack surfaces through document injection, embedding manipulation, and indirect prompt injection via ingested content.
  • LLM Output Handling and Downstream ExploitationModel output fed into code, SQL, HTML, or OS commands creates secondary vulnerabilities like XSS, injection, and command execution.
  • Threat Modelling for AI SystemsMid-level engineers must scope risks across the full pipeline: input validation, model behavior, tool policies, and output sinks.
  • AI-Assisted Code and Supply Chain RiskAI-generated code and dependency management introduce hallucination, poisoning, and trust issues that require security review and vetting.

Labs to practise

Hands-on labs on this site that match the work in this role. They run in the browser.

Courses that help

Tutorials to read

Mock interview questions

Ten questions from our AI Security Engineer question set, picked for this listing. Answer in your own words first, then open what a strong answer covers.

  1. An LLM agent has access to read_file, write_file, and fetch_url tools. Walk through a tool confusion attack that makes the agent do something it shouldn't. How would you detect and block it?

    What a strong answer covers
    • Agent hijacking via tool misuse
    • Tool policy design
    • Defense mechanisms
  2. An LLM generates SQL queries from natural language. Walk through a text-to-SQL injection attack that extracts data the user shouldn't see. How does the model's intermediate reasoning make this easier?

    What a strong answer covers
    • Downstream injection via model output
    • SQL injection via LLM generation
    • Output validation and parameterization
  3. An agent uses an HTTP tool to fetch URLs. Craft an indirect SSRF attack where you trick the agent into scanning internal IP ranges or cloud metadata endpoints. How does the agent's reasoning amplify the risk?

    What a strong answer covers
    • Agent-driven SSRF
    • Indirect exploitation
    • Internal network access via tool abuse
  4. You're designing approval gates: a human must review and approve before an agent takes sensitive actions. How could an attacker bypass this using a summary spoofing attack or other tricks?

    What a strong answer covers
    • Human-in-the-loop bypass
    • Approval flow exploitation
    • Adversarial summaries
  5. An LLM summarizes documents uploaded by users. If you upload a markdown file with hidden Unicode characters or special formatting, how could you inject commands that the model follows even if plaintext injection doesn't work?

    What a strong answer covers
    • Unicode and hidden character attacks
    • Encoding-based evasion
    • Format-agnostic injection
  6. You're threat modelling an LLM app that handles financial transactions. Map out the main attack surfaces (input, model behavior, tools, output) and rank them by severity for this use case.

    What a strong answer covers
    • End-to-end threat modelling
    • Risk prioritization
    • Business logic + AI intersection
  7. A developer pastes user data or API secrets into a prompt before sending it to an LLM. Walk through the risks: How could this leak even if the model doesn't repeat it? What context windows and logging matter?

    What a strong answer covers
    • Data hygiene in prompts
    • Context window exposure
    • Logging and observability risks
  8. An LLM is prompted to classify incoming emails as phishing or legitimate. Walk through an adversarial evasion attack that makes a phishing email slip past the classifier. Why is this especially hard to defend?

    What a strong answer covers
    • Adversarial ML examples
    • Classifier evasion
    • Robustness of AI security controls
  9. An LLM tool generates output meant for human consumption but it's also fed into code or commands. Walk through a scenario where valid-looking output causes harm downstream.

    What a strong answer covers
    • Output validation and trust
    • Downstream injection chains
    • Data vs. code boundaries
  10. You're designing a threat model for a large language model service. What are the top three attack surfaces unique to agents vs. chat-only models, and why does each matter?

    What a strong answer covers
    • Agent-specific threat vectors
    • Comparative security analysis
    • Architectural risk assessment

See the full question set for this kind of role

A 14-day preparation plan

  1. Days 1 to 3Foundation: Take OWASP Top 10 for LLM Applications course (5628) and Prompt Injection From Zero course (5533). Complete labs prompt-injection-1 and ai-jailbreak-roleplay-1 to understand direct and indirect attacks. Read the AI Agent Hijacking and Tool-Output Injection reading materials (5157, 5158) to contextualize wha
  2. Days 4 to 7Attack Depth: Work through ai-encoding-jailbreak-1, ai-system-leak-1, and ai-indirect-injection-1 labs to master evasion and extraction. Take Securing AI Agents and MCP course (5537) to understand agent architecture and hijacking. Complete the confused deputy (5160) and SSRF (5161) reading labs for real-world scenarios
  3. Days 8 to 11Output and Downstream Risk: Complete ai-data-exfil-1, ai-text-to-sql-injection-1, and ai-tool-arg-command-injection-1 to see how model outputs become exploitable. Read the Adversarial Document lab (5168) and Role-Confusion lab (5169). Focus on how injected instructions flow through tools and generate secondary vulnerab
  4. Days 12 to 14Integration and Defense: Finish ai-agent-hijack-1 and ai-llm-ssrf-1 for advanced multi-stage attacks. Review all 30 questions in mock interview format, focusing on threat modelling and defense reasoning. Build a personal checklist of attack vectors (direct injection, jailbreak, extraction, tool abuse, RAG poisoning, ou

Apply on Anthropic's siteBack to all roles

The interview questions, skills and plan on this page are SecurityElites practice material for this kind of role. They are not supplied or endorsed by Anthropic, and the real interview may differ.