Senior AI Developer with LLM Orchestration, Intelligent Knowledge Platform

Project overviewThis project focuses on building a next generation enterprise knowledge platform powered by large language models, semantic search, and graph technologies. The solution converts expert content into structured knowledge and enables advanced reasoning through agent driven workflows.TeamYou will collaborate within a cross functional team of AI engineers, backend developers, data engineers, and product specialists. The team operates in an agile environment with close collaboration, knowledge sharing, and iterative delivery practices.Position overviewWe are looking for an experienced AI Engineer to design and deliver advanced LLM powered solutions that transform unstructured information into scalable, searchable knowledge systems. You will work on building high quality retrieval and generation pipelines, enabling intelligent applications with strong evaluation, observability, and performance optimization practices.Technology stackPython, LangChain or similar orchestration frameworks, vector databases, embedding models, Google Cloud Spanner Graph, Gemini Enterprise Agent Platform, REST APIs, Docker, Kubernetes, ML evaluation frameworks, observability and tracing toolsResponsibilitiesDevelop and maintain end to end LLM orchestration and retrieval pipelinesDesign and implement embedding generation and chunking strategies with effective context window managementOptimize retrieval quality through tuning techniques and evaluation driven improvementsBuild entity extraction pipelines that transform unstructured content into graph structures using entity resolution and relationship normalizationImplement semantic search solutions and prompt engineering patternsDevelop agentic workflows to support complex reasoning tasksIntegrate graph databases with LLM based platforms and servicesCreate and maintain evaluation frameworks including ground truth datasets and regression testing processesMeasure and improve system performance using metrics such as recall, precision at K, answer relevance, and faithfulnessImprove observability, tracing, and cost efficiency across LLM pipelinesCollaborate with team members to design scalable and reliable systemsRequirementsExperience developing applications with large language models and retrieval augmented generationStrong proficiency in Python and backend development practicesHands on experience with vector databases and semantic search implementationsUnderstanding of embedding techniques, chunking strategies, and context managementExperience building or maintaining data pipelines for unstructured content processingFamiliarity with graph data modeling and knowledge graph conceptsExperience implementing evaluation methodologies for AI systems including precision and recall metricsExperience working with cloud platforms and containerized environments such as Docker and KubernetesAbility to design scalable and maintainable system architecturesStrong collaboration and communication skillsNice to haveExperience with Google Cloud services including Spanner GraphFamiliarity with Gemini Enterprise Agent Platform or similar toolsExperience with LangChain, LlamaIndex, or similar frameworksKnowledge of entity resolution and graph based reasoning techniquesExperience with observability tools for ML or AI systemsUnderstanding of cost optimization strategies for LLM usage