ML Engineer II

Key Responsibilities AI Automation & Agent Development Identify repetitive operational activities suitable for AI automation. Design, develop, deploy, and support AI agents, copilots, and automation tools. Develop prompt strategies, guardrails, evaluation frameworks, and feedback mechanisms. Build agent workflows with appropriate approval and escalation controls. Incident & Operational Intelligence Automate incident summarization, correlation, ticket routing, and impact analysis. Support root-cause investigation and remediation recommendations. Develop AI solutions for diagnostics across cloud, data, and integration platforms. Knowledge Management & RAG Build and maintain RAG solutions using runbooks, documentation, incident history, and support knowledge. Implement vector search, embeddings, and retrieval strategies. Improve knowledge discoverability and operational self-service capabilities. Enterprise Integrations Integrate AI solutions with ServiceNow, JIRA, GitLab, Datadog, CloudWatch, Databricks, OpenSearch, and collaboration platforms. Develop tool-calling capabilities to interact safely with operational systems. Governance & Reliability Implement human-in-the-loop controls and auditability. Ensure compliance with security, privacy, governance, and responsible AI principles. Monitor AI performance, adoption, accuracy, cost, and operational impact. Continuous Improvement Convert operational knowledge into reusable automation. Participate in incident response, postmortems, and operational readiness activities. Measure improvements in MTTR, MTTD, automation coverage, incident reduction, and support productivity.