Security Engineer – Agentic AI

Brahma

. Threat model agents, tools, MCP servers, and multi-agent workflows using OWASP Top 10 for LLM Applications, OWASP Agentic AI threats, and MITRE ATLAS .

Posted 11/11/2026full-timeRemote • United StatesMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in security engineering with a focus on application security, threat modeling, and risk management. Proficient in designing secure authentication and authorization mechanisms, as well as implementing security controls and automated testing for LLM applications.

Highest-signal resume keywords

Security EngineeringFluent PythonOAuth 2.0/OIDCThreat ModelingContainer Security

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Application SecuritySecurity ToolingAutomated TestingPrompt Injection MitigationWorkload IdentityLeast-Privilege DesignSecurity ScanningCI/CD IntegrationIncident ResponsePolicy-as-Code

Soft Skills

Risk CommunicationTeaching Security PracticesDocumentation Skills

Tools & Technologies

GarakPyRITPromptfooOPA/RegoCedarGVisorFirecrackerSeccompLandlockGCP IAM

Certifications & Qualifications

OSCPGIACCSSLP

Industry Keywords

ISO 27001ISO/IEC 42001SOC 2GDPRTPNNIST AI RMF

Tech Stack

Tools & technologies

CloudGoogle Cloud PlatformPython

About the role

Key responsibilities & impact

Threat model agents, tools, MCP servers, and multi-agent workflows using OWASP Top 10 for LLM Applications, OWASP Agentic AI threats, and MITRE ATLAS
Run a lightweight pre-launch security review gate
Review agentic code and designs, publish secure defaults, and make risk trade-offs explicit and owned
Teach secure agent practices through guides, threat-model walkthroughs, demos, and office hours
Design authentication and authorization for agents and tools using OAuth 2.0/OIDC, token exchange, scoped short-lived credentials, per-tool least privilege, and fail-closed MCP authorization
Harden containers and sandboxes with filesystem isolation, egress control, and human approval for irreversible actions
Build gateway defenses against prompt injection, tool abuse, excessive agency, and data exfiltration using input/output filtering, PII/DLP, and policy-as-code
Build automated adversarial tests for injection, tool misuse, exfiltration, and goal drift in CI and on a schedule
Govern MCP servers, skills, plugins, models, and dependencies through review, allow-listing, signing, SBOMs, and scanning
Make model, tool, and agent calls traceable and feed guardrail events and anomalies into monitoring and alerting
Monitor controls, tune guardrails, and keep them patched and current in production
Own agent-related incident response and lead technical response
Map controls to ISO 27001, ISO/IEC 42001, SOC 2, GDPR, and TPN and keep evidence audit-ready
Build controls, tooling, and tests; review code and designs; share security knowledge across Brahma teams
Follow emerging agent and AI threats, test new attack classes in bounded experiments, and bring proven defenses into production

Requirements

What you’ll need

5+ years in security engineering with a strong application or product security component
Fluent Python
Track record of shipping security tooling, controls, and automated tests as production code
Hands-on experience securing LLM applications or agents against prompt injection and unsafe tool use
Deep knowledge of OAuth 2.0, OIDC, token exchange, workload identity, and least-privilege design
Experience leading structured threat modelling and turning findings into prioritised engineering work
Experience embedding security scanning and checks into CI/CD
Experience securing containerised workloads
Ability to explain risk and trade-offs clearly to engineers and leadership, and to document decisions
Track record of teaching and documenting security practices for colleagues and other teams
Nice to have: experience with garak, PyRIT, promptfoo, or similar
Nice to have: practical use of OPA/Rego, Cedar, or similar
Nice to have: familiarity with gVisor, Firecracker, seccomp, or Landlock
Nice to have: experience building or securing MCP servers, LLM gateways, or guardrail services
Nice to have: working knowledge of GCP IAM, Workload Identity, Secret Manager, and Cloud Logging
Nice to have: exposure to ISO/IEC 42001, NIST AI RMF, or MPA/TPN content security
Nice to have: OSCP, GIAC, CSSLP, or equivalent certification

Benefits

Comp & perks

No formal on-call rotation yet, though one may be introduced