Staff Security Researcher – Offensive AI

. Run original offensive research against Dia, its agent, and backend services .

Posted 9/25/2026full-timeRemote • United States, CanadaLead💰 $225,000 - $300,000 per yearWebsite

Tools & technologies

CloudPythonSwiftTypeScriptGo

Key responsibilities & impact

Run original offensive research against Dia, its agent, and backend services
Investigate prompt injection and indirect exfiltration, tool-call abuse, permission and provenance bypass, sandbox escape, cross-profile data access, and quota and abuse-scoring bypass
Threat model new surface areas with product teams and review features before launch
Design and build automated vulnerability discovery, including model-driven code and infrastructure scanning, fuzzing harnesses, and agentic hunting pipelines
Collaborate with engineers to eliminate vulnerability classes and make issues structurally difficult to reintroduce
Define the standard for security testing before features ship
Survey commercial scanning services, frontier models, and open-source security models and deploy them against the codebase, infrastructure, and agent runtime
Plan and run regular AI-assisted red-team exercises and build attack corpora and harnesses
Shape pre-launch reviews for tools, integrations, agent capabilities, enterprise controls, and platform expansion
Report to the Head of Security and work across client, infrastructure, and product engineering

What you’ll need

8+ years in offensive security — vulnerability research, exploit development, red teaming, or product security testing — with a record of finding real bugs in software other people had already reviewed
Depth in at least one hard surface: LLM agent systems, browser or Chromium internals, OS sandboxing and native clients, or backend and cloud infrastructure — and the excitement to learn the rest
Practical fluency using LLMs as instruments, not just as targets, plus a working sense of when their output is noise
Production-quality coding in one or more of Go, TypeScript, Python, or Swift
Ability to write findings engineers act on and stay in the fix conversation without owning remediation
Ability to thrive in a high-trust, high-ambiguity environment
Resonance with company values
Primarily focused on hiring in North American time zones
4+ hours of overlap with team members in Eastern Time Zone

Comp & perks

Base salary, equity, and comprehensive benefits
Best-in-class benefits designed to support you, your family, and your life outside of work
Remote-first, distributed team
Option to work from the office in Brooklyn, New York
Startup-style impact, ownership, and ways of working