Key Responsibilities

AI Security &

- Guardrails

- Design, implement, and maintain enterprise AI security guardrails.

- Develop controls to mitigate prompt injection, jailbreaks, data leakage, hallucinations, model abuse, and adversarial attacks.

- Define AI trust, safety, governance, and security standards.

- Evaluate AI applications against organizational security, privacy, and compliance requirements.

- Establish policies and enforcement mechanisms for responsible AI usage.

AI Testing &

- Evaluation

- Design and develop AI testing harnesses to assess model performance, reliability, resiliency, and security.

- Create automated validation frameworks to test AI systems against approved success criteria.

- Develop benchmark testing methodologies for LLMs, agents, RAG platforms, and generative AI applications.

- Build continuous testing pipelines that validate changes before production deployment.

- Measure model quality, accuracy, consistency, safety, and business effectiveness.

AI Red Teaming

- Conduct AI red team assessments against enterprise AI applications.

- Develop adversarial testing scenarios and attack simulations.

- Identify and document vulnerabilities and weaknesses within AI systems.

- Perform threat modeling for AI-enabled business processes.

- Define remediation recommendations and compensating controls.

Engineering &

- Automation

- Develop Python-based automation for AI security and testing workflows.

- Build APIs, integrations, and orchestration frameworks supporting AI evaluation efforts.

- Integrate testing and governance controls into CI/CD pipelines.

- Create dashboards and reporting capabilities that provide visibility into AI risk and performance.

Collaboration &

- Leadership

- Partner with AI and application development teams to embed security throughout the AI lifecycle.





- Provide guidance on secure AI architecture patterns and implementation approaches.

- Mentor teams on AI security best practices.

- Stay current on emerging AI threats, frameworks, and regulatory developments.

Required Skills

AI/ML Technologies

- Large Language Models (GPT, Claude, Gemini, Llama, Mistral)

- Retrieval Augmented Generation (RAG)

- Agentic AI architectures

- Multi-agent systems

- Vector databases and embeddings

- Prompt engineering

- AI model evaluation methodologies

- Fine-tuning concepts and LLM optimization

Programming &

- Development

- Advanced Python development

- API development and integration

- Git/GitHub

- Automated testing frameworks

- CI/CD pipelines

- Containerization (Docker)

- Software Development Lifecycle (SDLC)

AI Security

- Prompt injection testing

- AI red teaming

- LLM security assessment

- Threat modeling

- Adversarial AI testing

- Secure AI architecture

- Data protection and privacy controls

- Responsible AI frameworks

AI Testing Frameworks

- Promptfoo

- DeepEval

- Ragas

- MLflow

- LangSmith

- Automated evaluation platforms

Cloud &

- Infrastructure

- Microsoft Azure

- Azure AI Foundry

- Azure OpenAI

- Azure Kubernetes Service (AKS)

- Kubernetes

- Monitoring and observability tooling

Security Frameworks

- OWASP Top 10 for LLM Applications

- NIST AI Risk Management Framework

- Secure coding standards

- Security assessments and vulnerability management

Qualifications

- Bachelor's degree in Computer Science, Engineering, Cybersecurity, or related discipline.

- 7+ years of software engineering, cybersecurity, or platform engineering experience.

- 3+ years working with AI/ML or Generative AI technologies.

- Demonstrated experience designing AI testing frameworks and security controls.

- Solid written and verbal communication skills.

- Ability to work effectively with both technical and business stakeholders.

📌 Senior AI Security Engineer (Bengaluru)
🏢 Naukri Assist
📍 Bengaluru