Agent Security Research Engineer
Obsidian SecuritySaaS Security company
Taipei, TaiwanSenior
Menlo Ventures
Norwest Venture Partners
IVP
Greylock
GV
Wing
Data & AI
About the role
TL;DR
Research and develop security content for AI agents.
- •You'll own agent security content from idea to production.
- •You'll research how AI agents can misbehave or be compromised.
- •Then you'll design the detection or policy, build it in our engines and pipelines, test it, ship it, document it, help customers adopt it, and tune it based on real-world results.
- •Key Responsibilities Research how AI agents can misbehave or be compromised.
- •Design detection or policy for agent security.
- •Build, test, ship, document, and tune security content.
- •Help customers adopt and tune security content.
- •Requirements Hands-on knowledge of how agentic tools work.
- •Solid grasp of agent-specific attack classes.
- •Strong SQL, ideally on analytical stores like ClickHouse, Databricks, or Snowflake.
- •Proficient scripting in Python or Go.
- •Working knowledge of SaaS and cloud identity (OAuth, PATs, API tokens, scopes) and developer tooling (Git, GitHub/GitLab, CI/CD).
Required skills
PythonSQLOAuthGitCI/CD
Nice-to-have skills
dbtDagster
Domain expertise
cybersecurity
Benefits & perks
Competitive compensation with equity and 401k, Comprehensive healthcare with dental and vision coverage, Flexible paid time off and paid holiday time off, 12 weeks of new parent or family leave, Personal and professional development resources
Tech stack
PythonSQLDatabricksSnowflakeOAuthGitCI/CDdbtDagster