ByteDance · Databases and retrieval
From knowledge ingestion to multimodal retrieval and vector engines.
Role and focus
ByteDance · Analytical Databases. Apr 2026 to Jul 2026. Role: Lakehouse and Retrieval Backend Engineer.
Delivered multi-source knowledge ingestion, hybrid retrieval, and multimodal indexing inside a database team, connecting data engineering, vector search, and production deployment.
Section sources
Published responsibilities
Completed an end-to-end knowledge pipeline for authentication, parsing, chunking, embedding, storage, hybrid recall, and reranking.
Validated layered scene and shot models for audio and video with multi-channel recall, RRF, and rerankers.
Contributed to vector-engine capabilities, system-table extensions, memory-store integration, and DiskANN indexing.
Section sources
Scope of this account
This record establishes the published responsibilities and technical direction. It does not provide internal architecture, customer data, a personal contribution percentage, or a verified numerical outcome. Personal projects are documented separately and should not be treated as company deliverables.