Description

Design and deploy machine learning models and LLM-based agents for enterprise security, threat classification, and risk scoring.

This role is on-site.

Responsibilities

• Build and deploy ML models for threat classification, anomaly detection, and risk scoring in production.
• Develop LLM-based agents for contextual reasoning, summarization, and workflow execution.
• Engineer prompt strategies and evaluation frameworks to ensure AI reliability and repeatability.
• Integrate AI outputs into enforcement platforms, including conditional access and device isolation logic.
• Partner with Data Engineering to build feature pipelines and production-ready datasets.

Required Skills

• 5+ years of hands-on AI/ML engineering experience.
• Proficiency in Python, PyTorch, and TensorFlow.
• Experience with LLM systems, prompt engineering, and agent-based workflows.
• Strong background in supervised and unsupervised learning techniques.
• Experience deploying production AI systems integrated into enterprise platforms.
• Knowledge of SDLC and system integration practices.
• Understanding of information security principles.
• Experience with data engineering and feature pipeline development.

Preferred Skills

• Experience with multi-agent orchestration systems and Microsoft Defender XDR.
• Familiarity with KQL, Microsoft Copilot Studio, and ServiceNow.
• Knowledge of AI governance, drift monitoring, and production lifecycle management.

Key Skills

Education

Any Graduate