Key skills
Cloud-native SystemsAPIsMicroservicesContainersServerless ArchitecturesAI/LLM-based SystemsRetrieval-Augmented Generation (RAG)Agent WorkflowsOrchestration WorkflowsTool Invocation PatternsAI PlatformsCI/CD PipelinesInfrastructure as CodeProduction ObservabilityPythonJavaDebuggingOptimizing Production SystemsAILLMOpenAIAnthropicRAGAutoGenLangGraphServerlessCI/CD
About this role
Rearc is a company dedicated to empowering engineers to build innovative products and experiences. They are seeking a hands-on AI Native Software Engineer to design, build, and deploy AI-driven systems in enterprise environments, focusing on production systems and integrating AI platforms.
Responsibilities:
- Design and implement AI agents, including RAG pipelines, orchestration workflows, and tool invocation
- Build evaluation frameworks to measure system accuracy, latency, and reliability
- Implement observability and monitoring across the AI system lifecycle
- Integrate with AI providers and build abstraction layers to support multi-model and multi-provider architectures
- Optimise AI systems for performance, cost, and scalability
- Develop cloud-native services using microservices, containers, and serverless patterns
- Build and deploy AI-powered applications aligned to business workflows
- Integrate AI systems into existing enterprise platforms and APIs
- Define and execute testing strategies for AI systems
- Measure and improve system performance (latency, throughput, accuracy, cost)
- Debug and optimise production systems
- Collaborate with client and internal engineering teams
- Participate in technical design discussions, focused on implementation
Requirements:
- 8–10+ years of software engineering experience
- Strong experience building cloud-native systems, including APIs, microservices, containers, and serverless architectures
- Proven experience building and deploying AI/LLM-based systems in production (e.g. RAG, agents, orchestration workflows)
- Hands-on experience with AI platforms (e.g. OpenAI, Anthropic, Google Vertex, or similar)
- Experience designing and implementing: + Retrieval systems (RAG) + Agent workflows and orchestration + Tool/function invocation patterns
- Strong understanding of system-level trade-offs (performance, cost, latency, reliability)
- Experience with CI/CD pipelines, infrastructure as code, and production observability
- Proficiency in Python, Java, or similar backend languages
- Experience debugging and optimising production systems
- Experience with agent frameworks (e.g. LangGraph, AutoGen, CrewAI)
- Experience designing multi-agent or distributed AI systems
- Familiarity with enterprise-scale system integration
- Experience optimising AI workloads for cost and performance