About this role
Design and implement production-grade agentic architectures leveraging LLMs and reasoning engines; build and optimise multi-agent systems, integrate external tools and knowledge bases, and tune agents for autonomy, adaptability, reliability, and safety. Prototype capabilities such as persistent memory, goal planning, and self-correction loops, and embed agentic AI into enterprise workflows while contributing to code reviews and documentation.
Skills for this role
PythonMachine LearningAI/ML frameworksLLMsPrompt engineeringLoRAQLoRALangChainAutoGenCrewAIAPI integrationMLOpsMLflowDVCExperiment trackingModel versioningDistributed systemsAzureAWSGoogle Cloud PlatformResponsible AISafety guardrailsLLM evaluationVector storesRetrieval systemsRAGAgentic architecturesMulti-agent systemsReasoning enginesPersistent memory