IT Supply Chain Analyst

You’ll help reduce repetitive operational work by identifying tasks that can be automated, building safe AI-assisted workflows, and improving how teams detect, diagnose, and prevent incidents. You’ll also help grow the team’s practical AI capabilities. • Identify and prioritize repetitive production-support tasks that can be simplified or automated, focusing on activities that consume significant team time or create avoidable manual effort. • Design, develop, test, and maintain operational automations for tasks such as health checks, data validation, ticket enrichment, incident summaries, and approved routine remediation. • Build AI-assisted workflows for incident triage, knowledge retrieval, runbook guidance, alert correlation, and remediation recommendations. • Apply agentic AI patterns to automate multi-step operational workflows, using clearly defined permissions, boundaries, approval steps, and fallback behavior. • Use predictive analytics and anomaly detection to identify operational patterns, anticipate potential issues, and trigger timely alerts or automated actions. • Integrate automation and AI solutions with approved monitoring, ticketing, knowledge-management, and Supply Chain systems through APIs and other supported interfaces. • Implement safeguards and quality controls including testing, access management, audit logging, output validation, human review, and safe failure handling. • Measure and improve automation outcomes by tracking time saved, manual effort reduced, accuracy, adoption, failure rates, and operational impact; document solutions and share reusable patterns with the team. Education: Bachelor’s or master’s degree in computer science, Engineering, Maths or Science Performed any modern NLP/LLM courses/open competitions is also welcomed. Technical Requirements: • Agentic AI workflows: Design multi-step AI-agent workflows with tool calling, state management, guardrails, human approvals, and fallback handling. • Python scripting: Build and test maintainable Python automations using tools such as pytest and Ruff. • Workflow automation: Automate repetitive operations using scripts, REST APIs, webhooks, and workflow orchestration tools. • GenAI and RAG: Integrate LLMs with prompts, approved knowledge sources, retrieval-augmented generation, and output evaluation. • Data and predictive analytics: Use SQL, pandas, and scikit-learn to analyze operational data and develop anomaly-detection or forecasting solutions. • Observability: Use monitoring, logging, and tracing tools to support automation; f • Security and quality: Apply least-privilege access, secure credential handling, audit logging, automated testing, and safe failure controls. • CI/CD and deployments: Configure Git-based pipelines for automated testing, deployment, approvals, and rollback. • Cloud fundamentals: Understand cloud services, identity and access management, networking, storage, compute, and cloud security. • Containers and infrastructure: Deploy and troubleshoot containerized workloads using Docker; Kubernetes or Terraform experience is preferred.