Frontier AI Security Threat Hunter

职位要求 / 描述

BUILD SOMETHING PEOPLE LOVE Wealthsimple is Canada’s leading financial innovator. The company offers a full suite of simple, sophisticated financial products across managed investing, do-it-yourself trading, cryptocurrency, tax filing, spending and saving. Wealthsimple currently serves more than 4 million Canadians and holds over $125 billion in assets under administration. The company was founded in 2014 by a team of financial experts and technology entrepreneurs, and is headquartered in Toronto, Canada. We're proud of what we've built — and we're just getting started. Read our Culture Manual https://www.wealthsimple.com/en-ca/culture and learn more about how we work https://www.wealthsimple.com/en-ca/careers. ABOUT THE TEAM We’re building a new AI-enabled adversarial testing capability whose mandate is simple but ambitious: find all the ways Wealthsimple can be exploited before our AI-enabled adversaries do. This group combines penetration testing, secure code analysis, and attack simulation R&D to continuously probe Wealthsimple’s systems using a combination of automation, autonomous AI agents, and human expertise. If you want to build an automated, end-to-end clearbox pentesting/red teaming platform, this is the team doing it! You’ll join as an individual contributor on this team, reporting into the Manager, Application Security, working alongside a platform engineer, security researcher, and the application security team. ABOUT THE ROLE As a Frontier AI Security Penetration Tester, you’ll be a hybrid builder and breaker: - Design and run automation-driven attack campaigns against Wealthsimple’s products and infrastructure including activities like: - Designing realistic AI attack scenarios that account for: - Attacker goals, initial access assumptions, and constraints. - Success criteria and clear boundaries for safety. - Wealthsimple-specific risks, design flaws, trust boundaries, and risk tolerance - Use and evolve our AI agents and tooling to: - Perform recon, vulnerability probing, confirmation, impact analysis, exploitation, and post-exploitation in safe environments. - Help shape and improve the automated testing pipeline: how we model assets, orchestrate agents, run automated workflows, and turn noisy outputs into actionable findings. You’ll work closely with a platform engineer and a researcher to - improve how scenarios and workflows are modeled and automated so we can automate the replay of promising attack paths. - build and improve AI agents and tooling - Propose and validate new tools or capabilities that unlock richer attack behavior - Learn to use our native and in-house tooling to find more - Work across the stack with platform engineers, AppSec, and other security teams to make automated and AI adversarial testing a routine, high-signal part of our SDLC. This includes: - reviewing AI-generated findings to separate high-impact vulnerabilities from noise and false positives. - Enhance proofs-of-concept into clear, reproducible steps for engineering teams and new automations - Support remediation by pairing with engineers when needed and verifying that fixes address the root cause. You’ll have substantial influence on the team’s roadmap through experimentation and R&D. PEOPLE WHO WILL SUCCEED IN THIS ROLE ARE - Courageously Ambitious - they enthusiastically tackle big audacious goals. - Deeply Human - they take responsibility for bringing the best out of themselves and others. - Problem Solvers - they have the ability and resilience to tackle complex issues, find common patterns, design solutions for scale, and see them through. - Enthusiastic Communicators - they capture and share learnings by default, and are always looking to implement suggestions for improvements and guardrails - Embraces change and experimentation - treat campaigns and framework changes as ex

技能关键字

职责方向