Staff Security Software Engineer, AI Security
New
D
DatabricksAI/ML Security
This role is open to candidates in the US (any location)Full-TimeStaff
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 7–10 years
- Required Skills
- PythonMLFlow
Requirements
- 7–10 years of experience in offensive security, AI/ML security research, or product security engineering.
- Subject matter expert in at least two AI security domains: LLM/Generative AI security, AI agent orchestration security, ML infrastructure security, or AI data governance.
- Demonstrated ability to design and execute adversarial attacks against production AI systems.
- Deep understanding of AI/ML platform architecture, including model training, serving, and trust boundaries.
- Expertise in at least one major cloud platform (AWS, Azure, GCP) and its AI/ML security model.
- Proficiency in Python with the ability to read ML model code, training scripts, and API serving code.
- Working knowledge of at least one additional language such as Go, Java, Scala, or Rust.
- Track record of driving cross-team security improvements and influencing product architecture.
- Experience building automated security tooling for AI systems.
- Strong communication skills with the ability to translate technical risks to non-technical stakeholders.
Responsibilities
- Lead AI red team engagements against production systems including Foundation Model APIs, RAG pipelines, and agentic workflows.
- Design and execute adversarial attack scenarios like prompt injection, jailbreaking, and cross-tenant data leakage.
- Perform security architecture reviews for complex AI features to identify and mitigate risks early in the design process.
- Develop automated security testing tooling, adversarial prompt libraries, and agent behavior analysis frameworks.
- Build and maintain security guardrails including LLM-as-judge reviews, output validation, and rate limiting.
- Drive cross-team remediation and set technical standards for AI security risk assessment and prioritization.
- Mentor team members on adversarial ML techniques and contribute to internal AI security knowledge assets.
View Full Description & ApplyYou'll be redirected to the employer's site
