Obsidian Security

SaaS security posture management

Agent Security Research Engineer

Security Engineering & ArchitectureConfirmed live in the last 24 hours

Full-timeTaipei City, TaiwanIn-person

About the Job

Requirements

Hands-on knowledge of how agentic tools work, including tool calling, hooks and lifecycle events, Model Context Protocol servers and transports, skills and plugins, and permission modes.
A solid grasp of agent-specific attack classes, including direct and indirect prompt injection, tool and description poisoning, confused-deputy and excessive-agency issues, secret leakage into context, and malicious or over-permissioned Model Context Protocol servers and extensions.
Ability to distinguish real risks from theoretical risks and explain the difference to customers.
Strong SQL skills, ideally with analytical stores such as ClickHouse, Databricks, or Snowflake.
A disciplined testing approach, including building reproducible positive and negative test cases before shipping content.
Proficiency in Python or Go scripting sufficient to build test harnesses, parse event logs, and perform detections.
Working knowledge of SaaS and cloud identity, including OAuth, personal access tokens, API tokens, and scopes, as well as developer tooling such as Git, GitHub or GitLab, and continuous integration and continuous delivery.
Ability to explain an agent attack chain to engineers, product teams, and customer-facing teams.

Responsibilities

Own agent security content from idea through production.
Research how AI agents, including coding assistants, desktop agents, workflow automation tools, and tools connected through the Model Context Protocol, can misbehave or be compromised.
Design detections or policies, build them into engines and pipelines, test, ship and document them, help customers adopt them, and tune them based on real-world results.
Be accountable for each content item delivering security value in customer environments.

Desired Qualifications

Published research, CVEs, talks, or blog posts on large language model or agent security.
Familiarity with threat detection.
Hands-on experience with endpoint security on macOS, Linux, or Windows.
Experience with dbt, Dagster, or other data-pipeline tooling.
Background in a SaaS security, cloud access security broker/SaaS security posture management, or insider-threat product.
Extensive daily use of Claude Code, Copilot, Cursor, or similar tools, and informed opinions about their security models.

Obsidian Security is a global leader in cyber security protecting the SaaS and non-human identity layer modern enterprises run on — from Salesforce and Snowflake to the AI agents now deployed inside them. The Obsidian Security platform gives unified visibility into every human and machine identity, app, and integration across their SaaS estate, detects identity-based and supply chain attacks in real time, and enforces least-privilege access before it's exploited. Trusted by major Fortune 500 companies T-Mobile, Workday, Snowflake, and S&P Global, Obsidian ranked No. 95 on the 2025 Deloitte Technology Fast 500™, growing nearly 1000% from 2021–2024 — helping CISOs turn an unmonitored attack surface into one they can govern with confidence. Obsidian has also been recognized by Forbes as America's Best Startup Employers in 2026.

In August 2026, Obsidian raised $85 million in Series D financing led by Crescent Cove Advisors, with participation from existing investors including Greylock Partners, Menlo Ventures, Norwest Venture Partners, IVP, Wing Ventures, and GV — pushing Obsidian's valuation to $1.1 billion, crossing into unicorn status. Obsidian is using the funding to deepen its R&D in agentic AI security and extend its platform as the standard for governing what AI agents can access and do inside third-party applications.

With global momentum, a growing partner ecosystem including SentinelOne, Databricks, and Google Cloud, and fresh capital from its Series D behind it, Obsidian is scaling rapidly toward long-term growth and IPO readiness.

Agent Security Research Engineer – Taiwan

About the role: You'll own agent security content from idea to production. You'll research how AI agents (coding assistants, desktop agents, workflow automation tools, and MCP-connected tools) 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. You're accountable for each piece of content delivering security value in customers' environments.

Required Skills:

Hands-on knowledge of how agentic tools work: tool calling, hooks and lifecycle events, MCP servers and transports, skills and plugins, permission modes
Solid grasp of agent-specific attack classes: direct and indirect prompt injection, tool and description poisoning, confused-deputy and excessive-agency issues, secret leakage into context, and malicious or over-permissioned MCP servers and extensions.
Able to tell real risk from theoretical risk and explain the difference to a customer.
Strong SQL, ideally on analytical stores like ClickHouse, Databricks, or Snowflake.
Disciplined about testing: builds reproducible test cases (positive and negative) before shipping content.
Proficient scripting in Python or Go, enough to build test harnesses, parse event logs, and perform detections.
Working knowledge of SaaS and cloud identity (OAuth, PATs, API tokens, scopes) and of developer tooling (Git, GitHub/GitLab, CI/CD).
Able to explain an agent attack chain to engineers, product and customer-facing teams.

Nice to Have:

Published research, CVEs, talks, or blog posts on LLM or agent security.
Familiarity with threat detection.
Hands-on experience with endpoint security on macOS, Linux, or Windows
Experience with dbt, Dagster, or other data-pipeline tooling.
Background in a SaaS security, CASB/SSPM, or insider-threat product.
Has used Claude Code, Copilot, Cursor, or similar heavily in daily work and has opinions about their security models.

Employee Benefits:

Our competitive benefits packages are designed to support our employees' well-being, both at work and at home. Our US based employees enjoy:

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

For more details on our US benefits, or for information on our international benefits, please see here.

About the Company

Obsidian Security

SaaS security posture management

Obsidian Security offers a security and posture management platform for enterprise SaaS environments. It connects to apps like Microsoft 365, Salesforce, Workday, and ServiceNow via APIs, collects configuration, user activity, and privilege data, and builds a Knowledge Graph that maps relationships across apps to detect account compromise, insider risk, excessive privileges, and configuration drift. The platform now includes AI governance features to discover and manage 'shadow AI', monitor AI agent behavior, and protect against token compromise and prompt injection. It differentiates itself with a cross-app knowledge-graph approach, headcount-based pricing, and a Fortune 500 customer base. Its goal is to give security and IT teams a single view and control plane for enterprise SaaS and AI-enabled ecosystems, reducing risk from misconfigurations and AI-related threats.

Company size: 201-500
Company stage: Series D
Total funding: $204.5M
Headquarters: Newport Beach, CA
Founded: 2017

Recently Posted Jobs

Explore more opportunities at Obsidian Security

See more jobs