Associate Security Researcher

Introduction

SpartanX Labs exists to discover tomorrow's attacks before they become today's incidents. We research offensive AI capabilities, benchmark autonomous security systems, identify emerging attack techniques, and accelerate the translation of research into product innovation. This is not a traditional penetration testing role.

You will help shape one of the industry's first dedicated AI Security Research organizations, working directly with executive leadership to influence the future of offensive AI. The ideal candidate is curious, highly technical, and passionate about solving difficult security problems through experimentation and innovation.

The Mission of the Role

The Associate Security Researcher is responsible for researching emerging threats, evaluating offensive AI capabilities, developing repeatable benchmarks, validating product security, and advancing the state of AI security research. This role blends offensive security, applied research, AI evaluation, product collaboration, and technical experimentation to produce measurable improvements across SpartanX's research and security capabilities.

Key Responsibilities

Offensive Security Research

• • Research emerging attack techniques targeting AI systems, cloud platforms, applications, and enterprise environments.
• • Develop proof-of-concept exploits and attack methodologies.
• • Analyze attacker tradecraft and evolving adversary techniques.
• • Perform vulnerability research and security validation activities.
• • Contribute to responsible disclosure and coordinated vulnerability reporting when appropriate.

AI Security Research

• • Evaluate offensive AI agents against realistic attack scenarios.
• • Research prompt injection, agent abuse, model exploitation, and autonomous attack techniques.
• • Develop new offensive AI workflows and evaluation methodologies.
• • Assess emerging AI technologies and identify opportunities to improve offensive capabilities.
• • Leverage AI-assisted research techniques to accelerate technical analysis while validating all outputs for technical accuracy and handling sensitive information appropriately.

Benchmarking and Research Automation

• • Design and maintain repeatable benchmark environments to objectively measure AI security capabilities.
• • Develop measurable success criteria, scoring methodologies, and performance metrics for research initiatives.
• • Integrate telemetry, automation, and operational metrics into research dashboards to measure capability improvements over time.
• • Promote reusable research methodologies, automation, and AI-assisted workflows that improve consistency, efficiency, and repeatability.

Product Security Research

• • Partner with Product, Engineering, and Security teams to validate product security capabilities.
• • Evaluate security controls against realistic attacker tradecraft and emerging threats.
• • Conduct research that directly informs product roadmap decisions.
• • Translate research findings into actionable product improvements and customer value.

Research Operations

• • Help develop repeatable research processes, methodologies, and technical standards across SpartanX Labs.
• • Collaborate with researchers to improve research quality, reproducibility, and operational efficiency.
• • Contribute to Bug Bounty initiatives, Attack Elements research, Benchmark Lab development, and future research programs.
• • Assist with the development of internal tooling, automation, and research infrastructure.

Technical Writing and Thought Leadership

Produce high-quality technical content including research papers, technical blogs, white papers, detection guidance, internal research documentation, conference submissions, and executive-ready research summaries and presentations.

Cross-Functional Collaboration

• • Validate offensive AI capabilities.
• • Support product engineering initiatives.
• • Evaluate security posture against emerging threats.
• • Collaborate with AI engineers, platform teams, and product leadership.
• • Improve the measurable effectiveness of research programs through data-driven decision making.

Core Technical Requirements (Must-Have)

• • 2 to 5 years of experience in offensive security, penetration testing, security research, vulnerability research, or red teaming.
• • Strong understanding of web application, cloud, operating system, and network security fundamentals.
• • Experience using Python, PowerShell, Bash, or similar scripting languages.
• • Familiarity with Burp Suite, Nmap, Metasploit, and common offensive security tooling.
• • Demonstrated ability to independently research technical problems and communicate findings.
• • Experience using AI tools to accelerate research, analysis, or security workflows while validating outputs for technical accuracy and handling sensitive information appropriately.

Desirable Skills & Experience (Nice-to-Have)

Preferred Experience (one or more of)

• • AI Security, Agentic AI, and Prompt Injection.
• • Cloud Security (AWS, Azure, GCP) and Kubernetes.
• • Active Directory, Threat Research, Malware Analysis, and Detection Engineering.
• • Benchmark Development, Infrastructure as Code, Security Automation, and Bug Bounty platforms.

Preferred Certifications

OSCP, PNPT, HTB CPTS, CRTO, eCPPT, Security+, AWS Security Specialty, AWS Solutions Architect, or CISSP (not required).

Success in the First 30 Days

You will become a technical lead or primary contributor for one or more strategic research initiatives, including:

• • AI Benchmark Lab
• • Offensive Agent Evaluation Framework
• • Bug Bounty Program
• • Novel Attack Research
• • Attack Elements Knowledge Base
• • AI Skill Evaluation
• • Research Automation
• • Product Validation
• • Research Publications

What We Are Looking For

We care less about years of experience and more about potential. The ideal candidate demonstrates:

• • Curiosity and a passion for learning.
• • Strong offensive security fundamentals.
• • A research mindset with attention to detail.
• • Excellent written and verbal communication.
• • Comfort working independently and collaboratively.
• • A bias toward experimentation and continuous improvement.
• • The ability to leverage AI to accelerate research while maintaining rigorous validation, auditability, and technical accuracy.

Career Progression

What We Offer

• • The opportunity to work at the forefront of offensive AI in 2026.
• • The chance to help shape one of the industry's first dedicated AI Security Research organizations.
• • Difficult, real-world problems across research, attack chains, reproducibility, evaluation, and tradecraft.
• • A high-ownership team with a culture of radical transparency and zero drama.
• • Flexibility and a focus on results (not hours).

Research Tooling and Focus Areas

• • Scripting: Python, PowerShell, Bash
• • Offensive Tooling: Burp Suite, Nmap, Metasploit
• • Cloud: AWS, Azure, GCP
• • Orchestration: Kubernetes
• • Focus Areas: Agentic AI, prompt injection, benchmarking, detection engineering, security automation