• Architect and own a multi-cloud (AWS/Azure) event-driven platform using Kubernetes/EKS, Terraform, AWS Batch, Celery, serverless APIs, FastAPI, and StoneBranch for orchestrated, autonomous agent workflows (LangChain, LangGraph, LlamaIndex, Pinecone). • Recruit, onboard, develop, and retain technical talent; conduct regular 1:1s, performance reviews, goal-setting, and annual/career planning for all engineers. • Lead sprint ceremonies (planning, retros, incident reviews), foster a collaborative culture, and mentor engineers on distributed async, agentic, and event-based system design. • Partner with Product Owners and business stakeholders to translate strategic goals into detailed architectural delivery plans. • Oversee and sign off technical designs including event contract/schema management, API gateway/token auth (OAuth2, Vault), vector DB (Pinecone) pipelines, and GenAI/LLM integration. • Drive process improvement: identify gaps in delivery velocity, quality coverage, and agile flow; sponsor retrospectives and adaptation. • Ensure system-wide observability, SLO/SLA definition, incident management, and production monitoring/alerting. • Promote transparent documentation/knowledge sharing (runbooks, API/event schemas, process playbooks). • Advocate and implement security/compliance policy, platform access control, and cross-team cost/data integrity management.