BambooHR Staff Application Security Engineer at BambooHR leads application security for AI features and agentic systems. This role involves setting security standards and architecting security agents to scale the security team's work.
Responsibilities
Lead security reviews and threat models of AI features and agentic systems — including autonomous agents, MCP servers, and third-party integrations — and keep review playbooks and quality criteria current
Set BambooHR's security standards for AI agents, covering identity and delegated authorization, tenant- and user-scoped data access, safe handling of tool output, tool supply chain, and human-approval requirements, and track adoption as threats evolve
Own the design of agents the security team uses for finding validation, triage, review assistance, and remediation — building and shipping them with clear evaluation criteria, bounded permissions, and human approval gates for high-impact actions
Help developers and security champions build and use agents safely through self-serve guidance and tooling, and advocate for the partner-team investment that work requires
Work with engineering and product leadership to embed security requirements into the SDLC, including design-time and release-time gates for AI features, and make agent-assisted code review, finding validation, and fix suggestions a default part of every team's CI/CD pipeline with clear blocking criteria and a fast exception path
Run security programs that span multiple teams and quarters — setting goals, milestones, and success metrics; maintaining a lightweight intake, prioritization, and retrospective cadence; coordinating dependencies across engineering, product, and operations; and reporting progress, risks, and tradeoffs to leadership
Represent AppSec in architecture forums, harmonize security requirements to reduce duplicated effort across teams, act as a point of escalation, and coach leaders on security tradeoffs
Partner with Legal, Privacy, and GRC on AI governance to close gaps between policy intent and technical implementation through guardrails and automation, including for emerging AI regulations
Train and coach software engineers and engineering teams on secure design and threat modeling, with emphasis on authentication, authorization, multi-tenancy, and AI features
Mentor fellow security engineers on technical direction and career growth, and close skill gaps on the security team through onboarding, training, and mentorship
Participate in an on-call rotation as needed to support incident response and resolve escalated security issues
Qualification
Bachelor's degree in Computer Science8+ years of experience in securityExperience mentoring engineers
Required
Bachelor's degree in Computer Science, Information Security, or a related field, or equivalent practical experience
8+ years of experience in security, including 5+ years of hands-on experience in application security
Experience securing multi-tenant SaaS platforms, including tenant isolation
Cloud and infrastructure security experience (e.g., AWS, Azure, GCP)
Hands-on experience building AI agents or agentic workflows, with concrete examples of how you handled permissions, failures, and validation — production systems, internal tools, personal or open-source projects, and substantial prototypes all count
Demonstrated ability to evaluate the security of AI and agentic systems, including prompt injection, tool and context poisoning, excessive agency, delegated authorization, data leakage, and supply-chain risk in models and tools; familiarity with the OWASP Top 10 for LLM Applications, the OWASP Top 10 for Agentic Applications, or comparable frameworks
Ability to design evaluations for agentic workflows covering task success, false positives and negatives, adversarial cases, and regression checks
Proven experience leading threat modeling (e.g., STRIDE, attack trees) and design reviews for complex applications and APIs
Deep understanding of web application and API security, including authentication and authorization (OAuth 2.0 scopes and delegation, OpenID Connect, token audience and validation), session management, and access control models
Strong software engineering skills in at least one language (e.g., Python, TypeScript, PHP), including testing and maintaining tools other people depend on
A track record of influencing without authority: leading cross-team initiatives, building business cases, and explaining technical risk in business terms to engineering, product, legal, and leadership audiences
Experience mentoring engineers, formally or informally
