Senior AI Security Engineer
Quarks Technosoft7–10 yrsBengaluru, Noida, PuneOn-siteDirect career pageEst. 25–45 LPA
Posted 1d ago
Reach people at Quarks Technosoft
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Quarks Technosoft you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Lead security efforts specifically targeting generative AI, large language models (LLMs), and agentic AI systems, focusing on red-teaming against prompt injection, jailbreaks, excessive agency, and model abuse.
- Develop and maintain production-quality test harnesses, automation, and tooling in Python to secure AI systems and integrate security checks into CI/CD pipelines.
- Analyze LLM application architectures and deliver clear, reproducible, and actionable security findings to engineering teams.
Minimum Requirements
- Bachelor's degree in any discipline, or equivalent professional experience.
- 6+ years in security engineering, application security, offensive security, detection engineering, or cloud security.
- 1-2 years hands-on experience securing or testing production generative AI, LLM, or agentic systems with demonstrated red-teaming results.
- Strong Python skills and solid cloud security engineering experience on a major hyperscaler (Azure preferred).
Ideal Candidate Profile
- Experienced in offensive or application security within AI/ML environments, with a specialization in adversarial testing of generative AI and LLM systems.
- Proficient in cloud security on major hyperscalers and skilled in embedding security automation into CI/CD and infrastructure-as-code workflows.
- Knowledgeable about AI/LLM architectures (embeddings, vector DBs, RAG, agent frameworks) and modern AI development tooling for fast security evaluation and tooling development.