Principal Security Researcher

Spellbook

1d•CA$201,500 - CA$252,000

About The Position

Legal teams worldwide trust Spellbook with their most sensitive data, and we're looking for a Principal Security Researcher to help us protect that trust at the source. You'll partner with the Director of Security & IT and work across the company to identify security risks, validate real-world impact, and reduce risk across Spellbook's products, infrastructure, AI workflows, and internal operations. This is a senior individual contributor role with broad influence. You'll move between original security research on legal AI and LLM-enabled workflows, hands-on offensive testing, secure product development partnerships with R&D and Engineering, and program-level work that raises the maturity of how Spellbook approaches red teaming, threat modelling, bug bounty triage, and incident response.

Requirements

Strong experience in application security, red teaming, penetration testing, vulnerability research, product security, or offensive security.
Hands-on experience testing modern web applications, APIs, authentication flows, authorization models, cloud services, and distributed systems.
Experience developing proof-of-concept exploits or clear technical demonstrations to validate security impact.
Firm grasp of common software security risks, secure design principles, identity and access controls, data protection, and secure development practices.
Experience partnering with engineering, product, or R&D teams to triage, prioritize, and remediate vulnerabilities end-to-end.
Excellent written and verbal communication skills, with the ability to write clear technical reports, executive summaries, remediation guidance, and public-facing research, and to explain trade-offs to engineers, PMs, and leadership.
Strong judgment around responsible disclosure, customer impact, confidentiality, and coordinated communication.
Pragmatic at distinguishing theoretical risk from practical risk, with the instinct to help teams focus on what matters most.
Comfortable operating with ambiguity and moving with urgency across hands-on testing, product security, incident support, and external coordination.
Track record of driving measurable risk reduction in a fast-moving technical environment.

Nice To Haves

Experience with AI security, LLM security, prompt injection, jailbreaks, agentic workflows, model abuse, or secure AI product development.
Experience in legaltech, fintech, healthtech, or another environment that handles highly sensitive customer data.
Experience managing or participating in bug bounty programs, responsible disclosure programs, or external researcher communities.
Experience publishing security research, speaking at conferences, or contributing to the broader security research community.
Familiarity with enterprise security expectations and compliance frameworks such as SOC 2, HIPAA, GDPR, or emerging AI governance frameworks.

Responsibilities

Identify security risks across the company and partner with the relevant teams to reduce them.
Lead active red teaming, application security testing, penetration testing, exploit validation, and adversarial analysis.
Conduct original security research on legal AI, LLM-enabled products, sensitive document workflows, prompt injection, data leakage, model misuse, and tool abuse.
Coordinate third-party penetration tests, red team exercises, audits, and other external security assessments.
Own external vulnerability reports — bug bounty submissions, responsible disclosure reports, researcher communications, triage, validation, prioritization, and remediation tracking.
Drive threat modelling and secure design reviews for new products, features, AI workflows, integrations, and infrastructure changes.
Partner with R&D and Engineering to surface trust boundaries, abuse cases, and data exposure risks early in development.
Support Security Operations during incident response by reproducing vulnerabilities, validating exploits, assessing impact, and recommending remediation.
Engage with frontier AI labs, external researchers, vendors, and the broader security community to stay current on AI safety and security developments.
Publish security research, advisories, technical writeups, blog posts, or conference talks where aligned with company priorities.
Define and improve repeatable processes for security research, testing, vulnerability management, and remediation across Spellbook.
Support with other responsibilities and projects as required.