<html><body><p>Responsibilities<br>Lead the design and development of scalable vectorization pipelines to convert text, PDFs, and multimodal data into high‑quality embeddings using models like BGE, Ada, or Cohere.<br>Manage and optimize vector databases (Pinecone, Weaviate, Milvus, pgvector), including building efficient indexing strategies (HNSW, DiskANN).<br>Develop advanced chunking and parsing techniques to maintain context and improve retrieval accuracy.<br>Build and fine‑tune hybrid search workflows combining dense vector search with sparse keyword methods (e.g., BM25).<br>Create evaluation frameworks and gold-standard datasets to measure retrieval performance (Hit Rate, MRR, Faithfulness).<br>Implement re-ranking pipelines using cross‑encoders to refine results before sending them to LLMs.<br>Work closely with engineering and product teams to ensure scalable, high‑performance retrieval syste</p></body></html>