Senior Red Team Operator, AI/LLM

Armadin

. Run full kill chains against LLMs, agents, RAG pipelines, and surrounding applications .

Posted 10/16/2026full-timeRemote • United StatesSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates deep expertise in AI offense, particularly in LLM and agent exploitation, with a strong ability to communicate complex attack narratives and make time-sensitive decisions. Proficient in scripting and automation for AI attacks, with a solid understanding of AI supply chains and security vulnerabilities.

Highest-signal resume keywords

AI Offense ExpertiseLLM ExploitationWeb And API ExploitationScripting In PythonBurp Suite Proficiency

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

LLM ExploitationPrompt InjectionData ExfiltrationAdversarial MLWeb ExploitationAPI ExploitationScripting In PythonScripting In BashModel-Serving StacksAI Supply Chain Security

Soft Skills

CommunicationSelf-DirectedDecision-MakingComfort With Ambiguity

Tools & Technologies

Burp SuiteCaidoGarakPyRITPromptfooAdversarial Robustness ToolboxLinuxWindowsMacOSMajor Cloud AI Platforms

Certifications & Qualifications

OSWEOSAIBurp Suite Certified PractitionerGWAPT

Industry Keywords

AI Attack ChainsAdversarial Input GenerationModel ExtractionMembership InferenceAI Supply ChainsMLOps InfrastructureAgent FrameworksRAG PipelinesTool AbuseHuman-In-The-Loop Safety

Tech Stack

Tools & technologies

CloudLinuxMacOSPython

About the role

Key responsibilities & impact

Run full kill chains against LLMs, agents, RAG pipelines, and surrounding applications
Chain prompt injection, tool abuse, and integration flaws into realistic attack paths
Turn jailbreaks and unusual model behavior into reproducible exploits with evidence of impact
Separate genuine risk from refusal-bypass noise
Map attack blast radius across tools, credentials, identity, cloud, and data
Exploit tool and function calling, MCP servers, plugins, memory, and multi-agent handoffs
Attack AI supply chains, including training data, embeddings, vector stores, model weights, serialization formats, and MLOps infrastructure
Review agent frameworks, orchestration logic, and model-serving code for vulnerabilities
Use black-box probing, adversarial input generation, model extraction, and membership inference
Translate AI attack tradecraft into techniques, decision logic, and evaluation data for autonomous agents
Pressure-test the swarm's models and agents and make human-in-the-loop safety and accuracy decisions
Build scripts, harnesses, and tools to automate AI attacks at scale
Deliver reports and debriefs explaining attack narratives, business risks, and remediation
Research emerging AI attack classes and feed findings into the platform
Balance concurrent operations and internal research with startup-level autonomy

Requirements

What you’ll need

Deep, hands-on AI offense, including LLM and agent exploitation beyond the OWASP Top 10 for LLM Applications
Experience with direct and indirect prompt injection, jailbreak chains, system prompt extraction, and data exfiltration through model outputs
Depth in at least one additional AI attack surface: agentic systems; RAG and data pipelines; adversarial ML; or AI supply chain and infrastructure
Strong web and API exploitation skills, including authentication and authorization bypass and injection chains
Fluency with Burp Suite, Caido, Garak, PyRIT, promptfoo, and the Adversarial Robustness Toolbox
Strong understanding of LLMs, agent frameworks, and model-serving stacks
Proficiency across Linux, Windows, and macOS
Proficiency with major cloud AI platforms
Scripting experience in Python, Bash, or similar
Experience using AI tools for reconnaissance, analysis, or tooling
Ability to make time-sensitive human-in-the-loop decisions and explain reasoning to safety and engineering teams
Scrappy, self-directed, and comfortable with ambiguity
Ability to communicate complex AI attack chains to engineers, executives, and legal counsel
Must be eligible to work in the United States without sponsorship
Ability 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 listed as even better

Benefits

Comp & perks

Full Health, Dental, & Vision Coverage
Meaningful Equity Ownership
In-Office Meals
Haircuts at the Office
Company Sponsored Conferences & Events
401(k), HSA, and FSA Plans
Flexible PTO