Senior Information Retrieval Engineer, Brand Concierge

What you'll do

• Architect and deploy scalable retrieval pipelines using vector databases like FAISS, Weaviate, Pinecone, or Qdrant.
• Implement semantic search infrastructure and hybrid systems combining semantic and keyword search methods.
• Build ingestion pipelines for structured and unstructured data including chunking strategies and embedding generation.
• Fine-tune relevance scoring, reranking algorithms, and query understanding mechanisms to improve precision and recall.
• Create and maintain knowledge graphs to support context linking and information disambiguation.
• Design and iterate on context window strategies to improve LLM reasoning and performance.
• Monitor key retrieval metrics such as accuracy, latency, and fallback rates while implementing caching and deduplication.

What we're looking for

• 4+ years of experience in data engineering, ML infrastructure, or information retrieval.
• Experience building and deploying RAG pipelines or semantic search systems.
• Strong proficiency in Python and machine learning libraries like Haystack, LangChain, or Elasticsearch.
• Proficiency with embedding models, vector similarity search, and document indexing.
• Familiarity with cloud platforms and MLOps tools such as Airflow, dbt, and Docker.
• Knowledge of graph databases or knowledge graph design is preferred.
• Experience optimizing retrieval for LLMs like OpenAI, Anthropic, or Mistral is preferred.
• A degree in Computer Science, Information Systems, or a related field is required.