Senior AI Engineer - LLM, RAG & Agent Systems

About The RoleWe are looking for a Senior AI Engineer to own the AI layer of our data platform—building production-grade LLM applications, retrieval systems, intelligent agents, and natural-language interfaces over enterprise data.You will work across RAG, embeddings, vector and hybrid search, agent/tool-calling architectures, LLM evaluation, and self-hosted open-weight models.This is a hands-on engineering role for someone who has moved beyond prototypes and has built, deployed, and operated LLM systems in production.What You'll OwnDesign and build production-grade LLM applications and RAG systemsOwn retrieval architecture including chunking, embeddings, vector search, hybrid search, and rerankingBuild agentic and tool-calling systems with appropriate permissions, scoping, validation, and guardrailsDevelop natural-language interfaces over enterprise data and structured databasesBuild and maintain LLM evaluation frameworks, including test sets, regression suites, grounding, hallucination, and answer-quality evaluationWork within our data platform and engineering stack rather than relying solely on hosted AI APIsDeploy and optimize self-hosted open-weight models using technologies such as vLLM or equivalent serving infrastructureOptimize inference performance, GPU utilization, latency, throughput, and costExplore and implement fine-tuning or model adaptation when appropriateCollaborate with data and software engineers to turn AI capabilities into reliable production productsRequired Qualifications5+ years of software or data engineering experienceAt least 2 years of hands-on experience building and deploying production LLM-based systemsStrong Python engineering skillsDeep understanding of RAG and retrieval architecture:Chunking strategiesEmbeddingsVector databases/searchHybrid searchRerankingRetrieval evaluationExperience building LLM agents or tool-calling systemsUnderstanding of permissions, access control, scoping, validation, and guardrails for AI systemsStrong understanding of LLM evaluation, including test datasets, regression testing, grounding, and hallucination detectionExperience working directly with data platforms, databases, or enterprise data, rather than only consuming hosted LLM APIsStrong software engineering fundamentals and experience taking systems from prototype to productionStrongly PreferredExperience with self-hosted open-weight modelsProduction experience with vLLM or equivalent model-serving infrastructureUnderstanding of GPU resource management and inference optimizationExperience with fine-tuning, LoRA, or other model-adaptation techniquesExperience with Text-to-SQL systemsExperience designing or using a semantic layer over real enterprise data modelsExperience combining unstructured documents with structured enterprise data in a single AI applicationWhat Success Looks LikeYou will be successful in this role if you can build an AI layer that is:Accurate — answers are grounded in enterprise dataReliable — quality is measured through automated evaluation and regression testingSecure — agents and tools respect user permissions and data boundariesScalable — models and retrieval infrastructure perform reliably in productionMaintainable — AI capabilities are built as production software, not isolated experimentsUseful — users can interact naturally with complex enterprise data