Description: Skills: AI Agents (AI Security Agent Engineer)

Experience Required: 7-12 years

Location: Chennai

Required Technical Skill Set : AI Security Engineering, LLM Security / Model Security, AI Red Teaming &

- Adversarial Testing, AI Governance &
- Guardrails, Security Data Science, Secure CI/CD Pipelines (DevSecOps / MLOps), Secure Configuration Management, Cloud Security (Azure / GCP / AWS), Python

Must-Have (Candidates must demonstrate depth in core areas and a blend/combination of the following specialisms)

- AI Security Engineering &
- Architecture: Deep hands-on experience designing and embedding security controls across Generative AI, Large Language Models (LLMs), Agentic workflows, and traditional ML pipelines.
- LLM / Model Security: Comprehensive mastery of AI vulnerability frameworks, specifically OWASP Top 10 for LLMs / GenAI (Prompt Injection, Model Inversion/Extraction, Data Poisoning, Insecure Output Handling, Training Data Poisoning) and MITRE ATLAS.
- AI Red Teaming &
- Adversarial Testing: Proven track record in executing adversarial simulations, prompt jailbreaking, bias/toxicity discovery, and red teaming on production LLMs/APIs using tools such as PyRIT, Garak, PromptFoo, ART (Adversarial Robustness Toolbox), or custom harnesses.
- AI Governance &
- Guardrails: Experience implementing runtime defensive guardrails, moderation APIs, input/output sanitisation, and policy filters (e.g., NeMo Guardrails, Llama Guard, Azure AI Content Safety, LangKit).
- Secure CI/CD Pipelines &
- MLOps: Practical experience embedding automated security gates, static/dynamic scanning, dependency verification, and container security into CI/CD / MLOps pipelines (GitHub Actions, GitLab CI, Azure DevOps, Jenkins).
- Secure Configuration Management &
- Cloud Security: Strong understanding of cloud security baselines, infrastructure-as-code (Terraform/Bicep), IAM least privilege, secret management, and secure configuration management across Azure, GCP, or AWS.
- Security Data Science &
- Coding:



Solid proficiency in Python and data analysis techniques applied to security telemetry, anomaly detection, automated threat modeling, and model evaluation.

Good-to-Have

- Direct exposure to enterprise AI platforms and orchestration frameworks (Azure OpenAI / AI Studio, Vertex AI, AWS Bedrock, MLflow, Kubeflow, LangChain, LlamaIndex).
- Understanding of AI Supply Chain security (AIBOM / SBOM, Hugging Face / Model Hub provenance verification, model weights signing).
- Knowledge of AI Governance standards & regulatory frameworks (NIST AI RMF, ISO/IEC 42001, EU AI Act, PRA/FCA guidelines).
- Industry certifications: CISSP, CCSP, AWS/Azure/GCP Security Specialty, CISM, or dedicated AI/ML security credentials.

SN Responsibility of / Expectations from the Role

1 AI Security Design &

- Threat Modeling: Conduct structured AI threat modeling (MITRE ATLAS, STRIDE) and security architecture reviews across enterprise AI initiatives, defining end-to-end security patterns for LLMs, RAG, and agentic systems.

2 Adversarial Testing &

- AI Red Teaming: Plan, execute, and document automated and manual red-teaming assessments to identify vulnerabilities such as prompt injection, context leakage, model evasion, and training data exposure.

3 Guardrail Engineering &

- Governance: Design, configure, and maintain scalable runtime guardrails and filtering layers to prevent toxic outputs, policy violations, and unauthorized tool invocation by AI models.

4 Pipeline &

- Configuration Automation: Integrate automated security testing, container scanning, model artifact verification, and configuration drift detection into CI/CD and MLOps release pipelines.

5 Security Data Science &

- Telemetry: Develop telemetry collection, anomaly detection, and logging mechanisms for model interactions to provide real-time security observability and threat detection.

6 Technical Leadership &

- Collaboration (Grade E/F): Act as a technical authority and mentor within the CSO capability, collaborating closely with CSO leadership (Louise Furniss / Julie Wilson), Data Science teams, Cloud Platform engineers, and external suppliers to ensure safe AI adoption across LBG.

📌 IND_Senior Security Engineer (Chennai)
🏢 Artech Infosystems
📍 Chennai