onsite
Gen AI Lead - RAG Specialist - Symhas
Software Engineer
Lead the design, build, and optimization of enterprise‑scale Retrieval‑Augmented Generation systems, driving intelligent search, Q&A, and knowledge management products with advanced vector store and embedding strategies.
About the role
Key Responsibilities
- Architect and deliver end‑to‑end RAG pipelines for large‑scale enterprise applications.
- Define and manage vector store strategy, selecting optimal embedding models and storage solutions.
- Implement advanced RAG patterns, including hybrid search, re‑ranking, and contextual retrieval.
- Collaborate with data, product, and engineering teams to integrate RAG into search, Q&A, and knowledge management products.
- Continuously evaluate and improve retrieval performance, latency, and scalability.
Requirements
- 5+ years of experience in AI/ML engineering with a focus on Retrieval‑Augmented Generation.
- Proficiency in vector databases (e.g., Pinecone, Weaviate, Milvus) and embedding model selection.
- Strong programming skills in Python and familiarity with cloud AI services (AWS, GCP, Azure).
- Experience designing hybrid search and re‑ranking pipelines for enterprise use cases.
- Excellent communication and leadership skills to guide cross‑functional teams.