Senior Red Team Operator, AI/LLM

This is a fully remote position, open to applicants in United States.

📋 Description

• Execute comprehensive kill chains against LLMs, agents, RAG pipelines, and associated applications.

• Integrate prompt injection, tool misuse, and integration vulnerabilities into plausible attack vectors.

• Convert jailbreaks and atypical model behaviors into replicable exploits, providing evidence of their impact.

• Distinguish real risks from bypass attempts that lack substance.

• Assess the attack blast radius across various tools, credentials, identities, cloud environments, and data.

• Leverage tool and function calling, MCP servers, plugins, memory, and multi-agent transitions for exploitation.

• Target AI supply chains, encompassing training data, embeddings, vector stores, model weights, serialization formats, and MLOps frameworks.

• Analyze agent frameworks, orchestration processes, and model-serving code for security flaws.

• Employ black-box probing, adversarial input generation, model extraction, and membership inference techniques.

• Transform AI attack strategies into methodologies, decision frameworks, and evaluation data for autonomous agents.

• Conduct pressure tests on the swarm's models and agents, making safety and accuracy decisions that incorporate human oversight.

• Develop scripts, harnesses, and tools to automate large-scale AI attack operations.

• Produce reports and debriefs that outline attack narratives, business implications, and remediation strategies.

• Investigate emerging AI attack classifications and integrate discoveries into the platform.

• Manage simultaneous operations and internal research while maintaining a startup-like degree of independence.

⛳️ Requirements

• Extensive, hands-on experience in AI offense, particularly in LLM and agent exploitation beyond the OWASP Top 10 for LLM Applications.

• Proficiency in both direct and indirect prompt injections, jailbreak sequences, system prompt extraction, and data exfiltration via model outputs.

• Expertise in at least one additional AI attack surface: agentic systems; RAG and data pipelines; adversarial machine learning; or AI supply chain and infrastructure.

• Strong skills in web and API exploitation, including authentication and authorization bypass, as well as injection chains.

• Familiarity with Burp Suite, Caido, Garak, PyRIT, promptfoo, and the Adversarial Robustness Toolbox.

• In-depth understanding of LLMs, agent frameworks, and model-serving architectures.

• Proficient in using Linux, Windows, and macOS environments.

• Experienced with major cloud AI platforms.

• Scripting proficiency in Python, Bash, or similar languages.

• Background in utilizing AI tools for reconnaissance, analysis, or tooling purposes.

• Capability to make timely human-in-the-loop decisions and articulate reasoning to safety and engineering teams.

• Resourceful, self-motivated, and able to navigate ambiguity effectively.

• Skilled in communicating intricate AI attack sequences to engineers, executives, and legal advisors.

• Must be authorized to work in the United States without the need for sponsorship.

• Willingness to travel up to 20% for on-site engagements or client meetings.

• Relevant certifications such as OSWE, OSAI, Burp Suite Certified Practitioner, GWAPT, or emerging AI security credentials are considered advantageous.

🏝️ Benefits

• Comprehensive Health, Dental, & Vision Coverage.

• Significant Equity Ownership Opportunities.

• In-Office Meal Provisions.

• On-Site Haircuts.

• Company-Sponsored Conferences & Events.

• 401(k), HSA, and FSA Plans.

• Flexible Paid Time Off.