Senior Security Engineer, AI/ML

Responsibilities

• Build and deploy GenAI applications using LangChain, LlamaIndex, or similar frameworks, and orchestrate agentic AI workflows.
• Design, train, and evaluate ML models spanning classical ML and deep learning, developing end-to-end pipelines.
• Implement and optimize RAG pipelines using embeddings and vector databases with built-in security controls.
• Conduct in-depth research on security vulnerabilities in LLMs, including prompt injection, jailbreaks, and adversarial attacks.
• Design and execute offensive security assessments and red teaming campaigns against GenAI and ML-powered systems.
• Collaborate cross-functionally to design secure AI-powered features and define hardening strategies.

Requirements

• 6+ years of experience in software engineering, machine learning, or security research (penetration testing/exploit development).
• Strong Python programming skills, including building APIs and backend components.
• Experience training ML models using Scikit-learn, TensorFlow, or PyTorch.
• Deep knowledge of LLM architectures, including transformers, embeddings, fine-tuning, and RAG.
• Hands-on experience with LangChain, LlamaIndex, or other GenAI frameworks.
• Familiarity with GenAI-specific risks such as prompt injection, model evasion, and data leakage.
• Working knowledge of SQL and Pandas for large-scale data processing.

Preferred Qualifications

• Background in AI/ML security red teaming or adversarial ML.
• Knowledge of vector database risks and AI model supply chain attacks.
• Experience with agentic tools such as AutoGen, CrewAI, or MetaGPT.
• Familiarity with cloud platforms (AWS, GCP, Azure) and MLOps tooling.
• Knowledge of threat modeling frameworks like STRIDE or MITRE ATLAS.

About the Company

Qualys is a leading provider of cloud-based security and compliance solutions, helping global customers secure their networks, devices, and applications through real-time visibility and analytics.