Principal AI Safety & Evaluation Engineer (Hybrid)

Threat X, Inc.; San Jose (CA); Hybrid; USD 225,000 - 245,000; Full time

Job summary

A10 Networks is seeking a Principal AI/ML Engineer to lead the technical strategy for protecting foundation models against misuse and jailbreaks. You will architect model-level defenses, drive evaluation pipelines, and mentor teams across safety, ML, and engineering in a hybrid work environment.

Required: 7+ years in applied ML or safety-critical systems, deep transformer knowledge, and leadership experience. Competitive compensation and strong collaboration with security and product teams.

Qualifications

• 7+ years of experience in applied machine learning, AI infrastructure, or safety-critical systems.
• Deep understanding of transformer-based architectures and safety interventions for LLMs.
• Proven expertise in analyzing adversarial behaviors, edge-case failures, and misuse scenarios.
• Ability to guide long-term technical strategy and mentor cross-functional teams.
• Strong written and verbal communication with experience influencing technical direction.
• Bachelor’s, Master’s, or PhD in Computer Science, ML, or related field.

Responsibilities

• Architect and lead the development of model-level defenses against jailbreaks, prompt injection, and policy violations.
• Define and drive evaluation strategies, including adversarial testing and stress-testing pipelines.
• Set technical direction for scalable mitigation techniques like safety-focused fine-tuning, prompt shielding, and post-processing methods.
• Collaborate with red teamers and researchers to convert threats into measurable evaluations and safeguards.
• Scale and improve human-in-the-loop pipelines for detecting toxic, biased, or non-compliant outputs.
• Stay up to date with LLM safety research and adversarial trends and apply insights to real-world defenses.

Job description

A10 Networks is seeking a Principal AI/ML Engineer to lead the technical strategy for protecting foundation models against misuse and jailbreaks. You will architect model-level defenses, drive evaluation pipelines, and mentor teams across safety, ML, and engineering in a hybrid work environment.

Required: 7+ years in applied ML or safety-critical systems, deep transformer knowledge, and leadership experience. Competitive compensation and strong collaboration with security and product teams.