Senior AI Search Engineer - RAG & LLM

Cacheflow; Seattle (WA); On-site; USD 185,000 - 230,000; Full time

Job summary

Otter.ai in Seattle seeks a Senior Software Engineer to own our enterprise search stack, focusing on retrieval augmented generation, embeddings, ranking, and scalable infrastructure.

You will design and optimize search components, implement NLP models, and collaborate with cross-functional teams to deliver accurate, fast search results. Requirements include a CS master’s, 5+ years in search/recommendation, and Python/C++ expertise.

Qualifications

• 5+ years of experience in search, recommendation, or question answering systems.
• Strong knowledge of relevance measurement, tuning, and modeling.
• Engineering experience with large language models and RAG systems.
• Familiarity with embedding-based search is a plus.

Responsibilities

• Design, develop, and oversee enterprise search infrastructure using vector databases, full-text search, and relational techniques.
• Develop deep learning NLP algorithms to analyze, reformulate and suggest search queries.
• Design, implement, and deploy ranking algorithms to deliver relevant results and improve UX.
• Evaluate and optimize algorithm accuracy using key metrics.
• Monitor end-to-end system performance and drive improvement initiatives.
• Stay updated with industry trends to align our search system with benchmarks.

Skills

Python

C++

Education

Masters degree in Computer Science

PhD (a plus)

Job description

Otter.ai in Seattle seeks a Senior Software Engineer to own our enterprise search stack, focusing on retrieval augmented generation, embeddings, ranking, and scalable infrastructure.

You will design and optimize search components, implement NLP models, and collaborate with cross-functional teams to deliver accurate, fast search results. Requirements include a CS master’s, 5+ years in search/recommendation, and Python/C++ expertise.