Senior Vector & Search Infrastructure Engineer

ByteDance; Seattle (WA); On-site; USD 242,000 - 456,000; Full time

Benefits offered by this job

Medical insurance

Dental insurance

Vision insurance

401(k) match

Paid parental leave

Job summary

ByteDance's Search team is building a fully managed information retrieval and analytics platform, integrating with Elasticsearch, OpenSearch, and Milvus to serve GenAI, search, security, and observability use cases. You will help advance vector and full-text search at scale, in a globally distributed, enterprise-grade environment.

Join us to push AI-powered search, RAG, and multimodal retrieval capabilities, collaborating with researchers and engineers to deliver impactful, production-grade

Qualifications

• BS in Computer Science, AI, ML, or related field.
• Strong software engineering in C++, Golang, Java, or Python.
• Experience with search engines, databases, or distributed systems.
• Hands-on experience with Elasticsearch/OpenSearch or Milvus.
• Strong understanding of distributed systems and performance optimization.

Responsibilities

• Develop and evolve Elasticsearch/OpenSearch and Milvus products for high-performance search and vector retrieval.
• Develop full-text and vector search, including hybrid and multi-vector retrieval.
• Optimize vector indexing and distributed retrieval across HNSW, IVF, DiskANN, etc.
• Explore cloud-native Vector Lakebase architectures for scalable search over data lakes.

Skills

Strong software engineering skills in

Experience with search engines

Distributed systems knowledge

Education

B.S in Computer Science, AI, ML, or related field

Tools

Elasticsearch/OpenSearch

Milvus

Job description

ByteDance's Search team is building a fully managed information retrieval and analytics platform, integrating with Elasticsearch, OpenSearch, and Milvus to serve GenAI, search, security, and observability use cases. You will help advance vector and full-text search at scale, in a globally distributed, enterprise-grade environment.

Join us to push AI-powered search, RAG, and multimodal retrieval capabilities, collaborating with researchers and engineers to deliver impactful, production-grade