Remote Vulnerability Researcher for AI Safety & Exploits

Bezel; United States; Remote; USD 96,000 - 165,000; Full time

Job summary

Parallel is hiring a Vulnerability Researcher for remote, contract work to help AI systems better distinguish benign prompts from malicious ones. You will apply advanced vulnerability research, reverse engineering, and exploit development to evaluate prompts, annotate intent, and improve model safety guidelines.

This is a remote, project-based role with scope and payment terms discussed before each assignment.

Qualifications

• Minimum five years of hands-on vulnerability research and reverse engineering.
• Experience discovering vulnerabilities using fuzzing, static and dynamic analysis, and patch diffing.
• Strong exploit development skills including memory corruption, heap exploitation, ROP, and mitigation bypasses (ASLR, DEP, CFI).
• Fluency with decompilers and debuggers (IDA, Ghidra, Binary Ninja; WinDbg, GDB, LLDB) across x86/x64 and ARM binaries.
• Deep understanding of the CVE lifecycle, n-day vs. 0-day research, and weaponization of PoCs.
• Strong written English to clearly document reasoning.
• Ability to work independently and handle complex problems.

Responsibilities

• Review ambiguous cybersecurity prompts to determine underlying intent and goal.
• Assess whether prompts reflect legitimate research or malicious attack preparation.
• Evaluate technical context, specificity, and real-world uplift a response would provide to attackers.
• Annotate prompts with accurate intent labels and concise rationales.
• Collaborate with researchers through dual-annotation and escalate disagreements to a reviewer.
• Identify emerging attack techniques and gaps to improve evaluation processes.

Skills

5+ years vulnerability research

Fuzzing

Static analysis

Dynamic analysis

Patch diffing

Exploit development

Memory corruption

Heap exploitation

ROP

ASLR

DEP

CFI

English writing

Independent work

Tools

IDA

Ghidra

Binary Ninja

WinDbg

GDB

LLDB

Job description

Parallel is hiring a Vulnerability Researcher for remote, contract work to help AI systems better distinguish benign prompts from malicious ones. You will apply advanced vulnerability research, reverse engineering, and exploit development to evaluate prompts, annotate intent, and improve model safety guidelines.

This is a remote, project-based role with scope and payment terms discussed before each assignment.