Research Scientist Graduate (AI Agent Memory Infrastructure) - 2026 Start (PhD)

ByteDance, San Jose, California

What you will do

Design, build, and evolve the next-generation memory infrastructure for AI agents, developing a unified platform that supports long-term memory, conversational memory, and task-oriented memory.
Architect and optimize memory system pipelines for large-scale, low-latency, and high-availability environments, including data ingestion, storage, indexing, retrieval, updating, compression, and forgetting mechanisms to support real-time inference and personalized interactions.
Explore key challenges at the intersection of large language models, context engineering, and data management, including memory representation, retrieval and ranking, conflict resolution, summarization and fusion, and memory lifecycle management.
Design unified memory models and processing workflows for multimodal data (text, image, audio, behavioral signals), enhancing agents’ long-term consistency, personalization, and task completion in complex scenarios.
Collaborate closely with model, application, and platform teams to productionize memory capabilities, and continuously optimize system performance across quality, latency, cost, reliability, and safety.

ByteDance, San Jose, California

Design, build, and evolve the next-generation memory infrastructure for AI agents, developing a unified platform that supports long-term memory, conversational memory, and task-oriented memory.
Architect and optimize memory system pipelines for large-scale, low-latency, and high-availability environments, including data ingestion, storage, indexing, retrieval, updating, compression, and forgetting mechanisms to support real-time inference and personalized interactions.
Explore key challenges at the intersection of large language models, context engineering, and data management, including memory representation, retrieval and ranking, conflict resolution, summarization and fusion, and memory lifecycle management.
Design unified memory models and processing workflows for multimodal data (text, image, audio, behavioral signals), enhancing agents’ long-term consistency, personalization, and task completion in complex scenarios.
Collaborate closely with model, application, and platform teams to productionize memory capabilities, and continuously optimize system performance across quality, latency, cost, reliability, and safety.