Senior Information Retrieval Engineer, Brand Concierge

Our Company Changing the world through digital experiences is what Adobe’s all about. We give everyone—from emerging artists to global brands—everything they need to design and deliver exceptional digital experiences! We’re passionate about empowering people to create beautiful and powerful images, videos, and apps, and transform how companies interact with customers across every screen. We’re on a mission to hire the very best and are committed to creating exceptional employee experiences where everyone is respected and has access to equal opportunity. We realize that new ideas can come from everywhere in the organization, and we know the next big idea could be yours! The Opportunity We are seeking a highly skilled Information Retrieval Engineer to lead the development and optimization of retrieval systems that power context-aware large language models (LLMs). This role focuses on building robust Retrieval-Augmented Generation (RAG) pipelines to ensure AI agents and applications have access to the most relevant, timely, and high-quality information. You'll work at the intersection of data engineering, machine learning, and knowledge management—enabling better reasoning, accuracy, and performance for enterprise-grade AI systems. What you'll Do RAG System Design Architect and deploy scalable retrieval pipelines using vector databases (e.g., FAISS, Weaviate, Pinecone, Qdrant) Implement semantic search infrastructure and hybrid retrieval systems (semantic + keyword) Data Processing & Ingestion Build ingestion pipelines for both structured and unstructured data sources Implement document chunking strategies, embedding generation (e.g., OpenAI, Cohere, HuggingFace), and metadata tagging Retrieval Optimization Fine-tune relevance scoring, reranking algorithms, and query understanding mechanisms Develop techniques to improve precision/recall for specific business domains or user tasks Knowledge Enhancement Create and maintain knowledge graphs to support context linking and disambiguation Manage data freshness and version control to ensure consistency and reliability of retrieved content Reasoning Support Design and iterate on context window strategies that improve LLM reasoning (e.g., adaptive injection, task-based retrieval) Collaborate with prompt engineers and model developers to align retrieval outputs with downstream model behavior Performance Monitoring Track key retrieval metrics such as accuracy, latency, and fallback rate Implement caching, prefetching, and deduplication strategies to optimize system responsiveness What you need to succeed 4+ years in data engineering, ML infrastructure, or information retrieval Experience building and deploying RAG pipelines or semantic search systems Strong Python skills and familiarity with retrieval libraries (e.g., Haystack, LangChain, Elasticsearch, Milvus) Proficiency with embedding models, vector similarity search, and document indexing Familiarity with cloud platforms and MLOps tooling (e.g., Airflow, dbt, Docker) Preferred Qualifications Knowledge of graph databases (e.g., Neo4j, TigerGraph) or knowledge graph design Experience optimizing retrieval for LLMs (e.g., OpenAI, Anthropic, Mistral) Background in IR/NLP, Search Engineering, or Cognitive Computing Degree in Computer Science, Information Systems, or a related field Our compensation reflects the cost of labor across several  U.S. geographic markets, and we pay differently based on those defined markets. The U.S. pay range for this position is $172,500 -- $306,625 annually. Pay within this range varies by work location and may also depend on job-related knowledge, skills, and experience. Your recruiter can share more about the specific salary range for the job location during the hiring process. In California, the pay range for this position is $211,800 - $306,625 At Adobe, for sales roles starting salaries are expressed as total target compensation (TTC = base + commission), and short-term incentives are in the form of sales ... (truncated, view full listing at source)