security
Posted Nov 7, 2025Senior Security Engineer AI/ML
at Qualys
Pune, IndiaOn-site
Responsibilities
- Design and execute offensive security assessments and red teaming campaigns for GenAI and ML-powered systems.
- Identify and classify novel threat vectors targeting model inference, training pipelines, and model-serving architectures.
- Collaborate with engineering and product teams to help design secure AI-powered features and define hardening strategies.
- Develop proof-of-concepts ( PoCs ), technical whitepapers, or blog posts on emerging threats and best practices.
- Monitor and analyze threat intelligence and academic research related to AI model security and supply chain risks.
Requirements
- Position Overview We are seeking an experienced and curious AI Security Researcher to explore and uncover vulnerabilities at the intersection of artificial intelligence, machine learning, and cybersecurity.
- You will play a critical role in identifying risks in LLM-powered systems, adversarial inputs, model manipulation techniques, prompt injection exploits, and other emerging AI threats.
- This role is perfect for someone who has a strong background in security research, a deep understanding of AI/ML systems and architectures, and a passion for red teaming, adversarial testing, and threat modeling in AI contexts. Key
- Responsibilities Conduct in-depth research on security vulnerabilities in LLMs and AI systems, including prompt injection, jailbreaks, data leakage, and adversarial attacks.
- Represent Qualys in security and AI research communities through speaking, publishing, or standardization efforts. Required
- experience in security research, penetration testing, or exploit development, with a focus on application or cloud security.
- Strong working knowledge of machine learning and LLM architectures (e.g., transformers, embeddings, fine-tuning, RAG).
- Familiarity with GenAI-specific risks such as prompt injection, model evasion, hallucination-based exploits, data leakage, or model theft.
- Experience in scripting and automation using Python (preferred) or similar languages for testing and PoC development.
- Hands-on understanding of LLM deployment scenarios (e.g., OpenAI, HuggingFace , custom-hosted models) and threat surfaces involved.
- Ability to analyze logs, API interactions, inference responses, and prompt chains to identify anomalous or risky behavior.
- Strong analytical mindset, technical writing skills, and the ability to communicate complex vulnerabilities clearly.
- Familiarity with responsible disclosure practices, bug bounty programs, or security research ethics. Preferred
- Qualifications Background in AI/ML security red teaming or adversarial ML. Knowledge of vector database risks, insecure RAG pipelines, model fingerprinting, and AI model supply chain attacks.
- Experience using or contributing to tools like LangChain , AutoGen , Guardrails.ai, LLM Guard, or Tracer.
- Familiarity with Secure SDLC, threat modeling frameworks (e.g., STRIDE, MITRE ATLAS), and AI-specific security checklists.
- Why Join Us? Leadership Impact: Be part of a security-first culture driving innovation in AI/ML safety at a global scale.
- Cutting-Edge Technology: Work on real-world security issues in LLMs and shape the defense landscape of next-gen AI systems.
Experience
- Qualifications 5+ years of
Benefits
- Competitive Compensation: We offer a comprehensive
- benefits package, including healthcare, retirement plans, and more.
Additional details
- Come work at a place where innovation and teamwork come together to support the most exciting missions in the world! Company Overview Qualys is a leading provider of cloud-based security and compliance solutions, processing vast amounts of data to help our global customers secure their networks, devices, and applications.
- With a strong focus on innovation and scale, Qualys empowers organizations to achieve continuous security and compliance through real-time visibility and analytics.
- As we continue to grow, we are looking for passionate and skilled professionals to join our mission in redefining the future of cybersecurity.
- Contribute to building internal tools for scanning, fuzzing, and automating LLM vulnerability discovery.
- Our Work Environment Collaborative & Transparent: We use virtual collaboration and pairing tools to share ideas openly.
- Siloed work is discouraged—teamwork is our strength.
- Agile & Flexible: We focus on delivering incremental value, adapting processes only when they serve our goals.
- Diverse & Inclusive: We believe in building teams with diverse perspectives, which fuels creativity and innovative problem-solving.
- People-Focused: Our people are our most valuable asset .
- We invest in personal growth and align individual strengths to company objectives .