Senior Security Engineer AI/ML
Qualys, Inc.1 hour ago
Pune, IndiaSenior
Responsibilities
- Research vulnerabilities in LLMs, GenAI systems, and ML systems, including prompt injection, jailbreaks, data leakage, and adversarial attacks.
- Design and execute offensive security assessments and red-team campaigns for GenAI and ML-powered systems.
- Identify threat vectors affecting model inference, training pipelines, model serving, and AI supply chains.
- Partner with engineering and product teams to design secure AI features and define hardening strategies.
- Develop proof-of-concepts, technical whitepapers, and blog posts on emerging AI security threats.
- Analyze threat intelligence and academic research related to AI model security.
- Build internal tools for scanning, fuzzing, and automating LLM vulnerability discovery.
- Represent Qualys through security research speaking, publishing, and standardization activities.
Requirements
- 5+ years of experience in security research, penetration testing, or exploit development, focused on application or cloud security.
- Strong working knowledge of machine learning and LLM architectures, including transformers, embeddings, fine-tuning, and RAG.
- Familiarity with GenAI risks such as prompt injection, model evasion, hallucination-based exploits, data leakage, and model theft.
- Experience with Python or similar scripting languages for testing and proof-of-concept development.
- Hands-on understanding of LLM deployments using OpenAI, Hugging Face, or custom-hosted models.
- Ability to analyze logs, API interactions, inference responses, and prompt chains for anomalous or risky behavior.
- Strong analytical, technical writing, and communication skills.
- Familiarity with responsible disclosure, bug bounty programs, or security research ethics.
- Preferred: AI/ML security red teaming or adversarial ML experience; knowledge of vector database risks, insecure RAG pipelines, model fingerprinting, and AI supply-chain attacks.
- Preferred: experience with LangChain, AutoGen, Guardrails.ai, LLM Guard, or Tracer.
- Preferred: security research publications or presentations and familiarity with Secure SDLC, STRIDE, MITRE ATLAS, and AI-specific security checklists.
Benefits
- Comprehensive benefits package including healthcare and retirement plans.
- Mentorship, professional growth resources, and exposure to cutting-edge research.
- Collaborative virtual work environment with pairing and knowledge-sharing tools.
- Inclusive culture focused on teamwork, diverse perspectives, and personal growth.