• Design and deploy machine learning models for threat classification, anomaly detection, and risk scoring.

• Build LLM-based agents capable of contextual reasoning, summarization, classification, and workflow execution.

• Engineer prompt strategies and structured evaluation frameworks to ensure reliability and repeatability.

• Develop multi-agent systems that automate operational tasks and drive measurable workforce efficiency gains.

• Integrate AI outputs into enforcement platforms (e.g., conditional access triggers, device isolation logic, adaptive workflows).

• Implement regression, classification, clustering, or anomaly detection models aligned to real-world telemetry.

• Design guardrails, kill switches, and rollback mechanisms to ensure safe AI deployment in regulated environments.

• Partner with Data Engineering to develop feature pipelines and production-ready datasets.

• Build model monitoring and feedback loops to continuously improve precision and reduce false positives.

• Contribute to ontology-driven reasoning and entity-aware AI decisioning where applicable.

What will you do in this role

• 3–6+ years of hands-on AI/ML engineering experience.

• Strong proficiency in Python and modern ML frameworks (e.g., scikit-learn, PyTorch, TensorFlow, or equivalent).

• Experience deploying production AI systems integrated into enterprise platforms or APIs.

• Demonstrated experience with LLM-based systems, prompt engineering, or agent-based workflows.

• Strong understanding of supervised and unsupervised learning techniques.

• Experience building evaluation metrics for model performance and business impact.

• Ability to translate ambiguous operational problems into structured AI solutions.

• Strong systems-thinking mindset and engineering discipline.

What should you have

• Experience building multi-agent orchestration systems.

• Familiarity with Microsoft Defender XDR, Sentinel, KQL, or related security platforms.

• Experience with Microsoft Copilot Studio or similar enterprise AI orchestration tools.

• Exposure to MITRE ATT&CK mapping, risk engines, or behavioral threat modeling.

• Experience integrating AI outputs into automation platforms (ServiceNow, Logic Apps, API-driven workflows).

• Experience implementing AI governance, drift monitoring, and production lifecycle management.

  • Familiarity with graph-based reasoning or ontology-driven AI models.