(ind) Systems and Infrastructure Engineer Ii, Information Security

Walmart Walmart · Retail · Chennai, India

This role focuses on designing, building, testing, and monitoring AI systems to protect them from sophisticated attacks and ensure compliance. It involves implementing prompt validators, redaction logic, developing telemetry, and assisting in incident response for AI systems. The role requires a blend of software engineering, cybersecurity, and AI/ML knowledge, with a focus on AI security and safety.

What you'd actually do

  1. Contribute to CI test corpora (e.g., SafetyPrompts, JailbreakBench)
  2. Implement prompt validators and redaction logic (e.g., Presidio)
  3. Develop telemetry fields and logging scaffolds (e.g., prompt_hash, model_version)
  4. Assist in incident reproduction, red-team tracking, and triage
  5. Write test harness code and review pull requests for safety tests

Skills

Required

  • Python
  • Secure coding practices
  • SDLC awareness
  • DevSecOps tooling integration
  • ML fundamentals
  • ML frameworks (PyTorch, TensorFlow, scikit-learn)
  • AI/ML threats (evasion, poisoning, model inversion, prompt injection)
  • Vulnerability scanning
  • Threat modeling
  • Containerized/cloud environments (Docker, Kubernetes, GCP/Azure)
  • Cryptography
  • Authentication
  • IAM principles
  • Data access controls
  • Input sanitation
  • Training data protection
  • Federated learning
  • Differential privacy
  • Zero Trust principles
  • AI-specific IR workflows
  • Algorithmic fairness
  • Bias
  • Safety guardrails
  • Problem-solving
  • Analytical thinking
  • Communication
  • Collaboration
  • Adaptability
  • CI test corpora contribution
  • Prompt validator implementation
  • Redaction logic implementation
  • Telemetry field development
  • Logging scaffold development
  • Incident reproduction assistance
  • Red-team tracking assistance
  • Triage assistance
  • Test harness code writing
  • Pull request review for safety tests
  • Bachelor’s of Engineering with Specialization in Cybersecurity / AI
  • Minimum 6 months Internship working on A Security & Safety Engineering Projects
  • Experience in Python, CI/CD, test writing, JSON/YAML schema

Nice to have

  • Prompt safety experimentation
  • Basic classifier integration
  • Prior exposure to red-team scenarios
  • PII protection workflows
  • Applied ML security
  • MLSecOps

What the JD emphasized

  • Python (required)
  • Secure coding practices
  • Familiarity with ML fundamentals and frameworks (PyTorch, TensorFlow, scikit-learn)
  • Understanding threats like evasion, poisoning, model inversion, prompt injection
  • Exposure to vulnerability scanning and threat modeling
  • Familiar with GDPR, HIPAA, ISO 27001, and NIST AI RMF basics
  • Recognize algorithmic fairness, bias, and safety guardrails
  • Bachelor’s of Engineering with Specialization in Cybersecurity / AI
  • Completed minimum 6 months Internship working on A Security & Safety Engineering Projects
  • Experience in Python, CI/CD, test writing, JSON/YAML schema

Other signals

  • AI Security
  • AI Safety
  • MLSecOps
  • Threat-informed prompt testing
  • Prompt injection
  • Evasion
  • Poisoning
  • Model inversion