Job TitleWhat You Must Have8–10+ years of software engineering experienceStrong experience with cloud-native systems (APIs, microservices, containers, serverless)Experience building and deploying AI/LLM-based systems in production (agents, RAG, orchestration)Proficiency in Python, Java, or similar backend languagesExperience with: CI/CD pipelinesInfrastructure as CodeMonitoring and observability toolsHands-on experience with AI platforms (OpenAI, Claude, Vertex AI, or similar)What We'd Like You to HaveExperience with agent frameworks (e.g., LangGraph, AutoGen, CrewAI)Experience designing multi-agent or distributed AI systemsFamiliarity with enterprise-scale system integrationExperience optimizing AI workloads for cost and performanceResponsibilities Will IncludeDesign and implement AI agents, including: Retrieval (RAG)Orchestration workflowsTool/function invocationPolicy-based routingBuild evaluation frameworks for accuracy, latency, and reliabilityImplement observability and monitoring for agent lifecycleAI Platform Integration Integrate with AI providers (e.g., OpenAI, Anthropic, Google Vertex, open-source models)Build abstraction layers to support multi-model and multi-provider architecturesOptimize model usage for performance, cost, and latencyCloud-Native Development Develop scalable services using: Microservices architectureContainers (Docker, Kubernetes)Serverless and event-driven patternsImplement CI/CD pipelines and infrastructure as code (e.g., Terraform, Helm)Ensure production readiness, logging, monitoring, and fault toleranceApplication Development Build and deploy AI-powered applications aligned to business workflowsIntegrate AI systems into existing enterprise platforms and APIsDevelop backend services and APIs supporting agent workflowsTesting & Performance Define and execute test strategies for AI systemsMeasure system performance (latency, throughput, accuracy, cost)