Staff AI Security Engineer - Red Team & Tooling

Menlo Ventures; California (MO); On-site; USD 180,000 - 240,000; Full time

Job summary

Databricks is seeking a Staff Security Software Engineer for the AI Security team to lead defensive and offensive security work across AI/ML capabilities. You will set security standards, drive cross‑team remediation, and mentor engineers in both offensive techniques and secure AI design.

You will conduct AI red team engagements, perform architecture reviews, and build scalable tooling to automate threat modeling, vulnerability triage, and guardrails across Databricks’ AI platform.

Qualifications

• 7–10 years of experience in offensive security, AI/ML security research, or product security engineering.
• Expert in at least two AI security domains (e.g., LLM security, AI agent security, ML infrastructure security, data governance).
• Demonstrated ability to design and execute adversarial attacks against production AI systems.
• Deep understanding of AI/ML platform architecture and trust boundaries between components.
• Expert in at least one major cloud platform (AWS, Azure, GCP) and proficient in Python; working knowledge of another language.

Responsibilities

• Lead AI red team engagements against Databricks' production AI systems (Foundation Model APIs, Genie, Model Serving, MCP‑connected agents, RAG pipelines).
• Design and execute adversarial attack scenarios and develop PoC exploits.
• Evolve the Databricks AI Security Framework (DASF) with risk taxonomy and testing methodology.
• Perform security architecture reviews for complex AI features and partner with AI/ML teams to implement scalable controls.
• Develop automated security tooling for AI systems and build guardrails (LLM-as-judge, prompt delimiting, audit logging).
• Mentor engineers, contribute to training materials, and represent Databricks in AI security forums.

Skills

AI security

Adversarial ML

Cloud security

Python

Communication

Security tooling

Tools

MLflow

Unity Catalog

Delta Lake

Job description

Databricks is seeking a Staff Security Software Engineer for the AI Security team to lead defensive and offensive security work across AI/ML capabilities. You will set security standards, drive cross‑team remediation, and mentor engineers in both offensive techniques and secure AI design.

You will conduct AI red team engagements, perform architecture reviews, and build scalable tooling to automate threat modeling, vulnerability triage, and guardrails across Databricks’ AI platform.