Staff Security Software Engineer, AI Security

This is a fully remote position, open to applicants in California.

📋 Description

• In the role of Staff Security Software Engineer within the AI Security team, you will be a senior technical authority who establishes the benchmarks for securing Databricks' AI and ML functionalities.

• You will spearhead AI red team initiatives against operational AI systems, perform security architecture assessments for intricate, multi-system AI features, and develop the tools and frameworks that enhance the team's effectiveness.

• As a subject matter expert in at least two AI security areas, you will operate with a high degree of independence—leading cross-team remediation efforts, establishing technical benchmarks, and mentoring colleagues in both offensive strategies and secure AI design practices.

⛳️ Requirements

• 7–10 years of combined experience in offensive security, AI/ML security research, or product security engineering, showcasing leadership in securing complex systems.

• Subject matter expert in at least two of the following AI security domains:

• - LLM and generative AI security (prompt injection, jailbreaking, training data extraction)

• - AI agent and orchestration security (MCP, memory sharing, multi-agent systems)

• - ML infrastructure and serving security (model serving multi-tenancy risks, training infrastructure security)

• - AI data governance and privacy (fine-grained access control, data residency, inference data isolation)

• Proven ability to design and implement adversarial attacks on production AI systems.

• In-depth knowledge of AI/ML platform architecture—understanding how models are trained, served, and integrated, as well as identifying the trust boundaries between components.

• Proficient in at least one major cloud platform (AWS, Azure, GCP) and familiar with its AI/ML security model.

• Skilled in Python; capable of reading and analyzing ML model code, training scripts, and API serving code; knowledge of at least one additional programming language (Go, Java, Scala, Rust) is also required.

• A proven history of driving enhancements in cross-team AI security and influencing product architecture decisions.

• Experience in developing automated security tools for AI systems.

• Excellent communication skills—able to articulate AI security risks into actionable recommendations for engineers, product managers, and leaders.

• A practical approach to risk—able to differentiate between real-world exploitable AI risks and theoretical concerns.

🏝️ Benefits

• Comprehensive benefits and perks that cater to the needs of all employees. For specific details regarding the benefits available in your region, click here.