Security Researcher

Aspiron Search; New York (NY); Hybrid; USD 160,000 - 230,000; Full time

Benefits offered by this job

Stock options

Flexible work hours

Job summary

Aspiron is seeking a founding Security Researcher in New York City to lead and build the research function from the ground up. You will work directly with the founders, owning the research division as the firm scales, and you will shape the future of AI security across enterprise deployments.

You will break things to understand threats, reverse engineer attacks on AI agents, and develop PoC exploits and detection methods for prompt injection, tool abuse, data exfiltration, and persistence.

Qualifications

• Minimum 5+ years in offensive security or red teaming.
• Track record of analyzing real-world attacks.
• Strong engineering skills to build PoCs quickly.
• Published papers, blogs or open source projects.
• Experience with AI agents or AI security.
• Experience with security research and open source projects.
• Speaking at security conferences (e.g., Black Hat).

Responsibilities

• Lead and build research function from ground up.
• Investigate real-world AI agent attacks and develop detection methods.
• Build lab, automation, and evaluation harnesses.
• Publish research under your own name.

Skills

Offensive security

Red teaming

Research tooling

Publications

AI security

Public speaking

LLM security

Open source

Security research

Black Hat talks

Job description

Founding Security Researcher- New York City (hybrid)

Aspiron is retained by an AI security startup who are filling a critical gap in the AI Detection & Response space by building the runtime security layer that finally makes AI agent activity visible and controllable across the enterprise

Their open source foundation has already been recognized as one of the hottest tools in cyber and they have impressive growth plans for the next 18-months.

Now, they're in the process of looking for the person to lead and build the research function from the ground up - working directly with the two founders and owning the research division as the firm continues to grow.

What you'll actually be doing

Break things first, Investigate real-world attacks on AI agents and autonomous systems along with discovering novel attack techniques across coding agents, MCPs, CI pipelines, and developer tools. You'll be tasked to reverse engineer emerging threats and build PoC exploits that push the frontier of AI security to finally turn it into product, developing new detection methodologies for prompt injection, tool abuse, data exfiltration, agent persistence etc.

You’ll also build the lab. This is the internal frameworks, automation, and evaluation harnesses that let you discover and reproduce attacks systematically across every agent framework that matters. And you'll publish under your own name.

What we’re looking for

• 5+ years in offensive security, red teaming, detection engineering, or vulnerability research
• A track record of finding and analyzing sophisticated real-world attacks
• Strong engineering skills. can you build research tooling and PoCs fast, not just find bugs and move on
• Published work: papers, blogs, deep dives, open source projects etc.
• Deep, genuine curiosity about AI systems,
• High agency and comfort building something from zero
• A name people already recognize in offensive security or security research
• Experience with AI agents, LLM infrastructure, or AI security specifically
• Offensive tooling, or open source projects with real adoption
• Black Hat, DEF CON, USENIX, or similar speaking experience