Senior / Information Retrieval Engineer (AI/ML), Brand Concierge
San Jose
Workplace: OnsiteFull timeFunction: Hospitality & Food ServiceExperience: 4+ yearsSkills: ["Vector databases","Semantic search","Embedding models","Python","Machine learning","Information retrieval","Data engineering","Mlops","Airflow","Dbt","Docker","Elasticsearch","Milvus","LangChain","Haystack","Weaviate","Pinecone","Qdrant","OpenAI","Cohere"]Lead development of Retrieval-Augmented Generation (RAG) pipelines and retrieval systems for enterprise-grade AI. Design scalable, vector-based retrieval architectures, integrate semantic/keyword search, and optimize retrieval quality. Collaborate with prompt and model teams to improve LLM reasoning, accuracy, and system performance in real-world AI applications.
Loading
Loading job details...
Preparing the role view and application actions.

