Research Scientist - AI Agent Memory Infrastructure - Global Frontier Tech Recruitment Program - 2027 Start (PhD)
ByteDanceResponsibilities
- Design and build unified memory infrastructure supporting long-term, conversational, and task-oriented memory for AI agents.
- Architect and optimize large-scale, low-latency, highly available pipelines for data ingestion, storage, indexing, retrieval, updating, compression, and forgetting.
- Research memory representation, retrieval and ranking, conflict resolution, summarization, fusion, context engineering, and memory lifecycle management.
- Develop multimodal memory workflows for text, image, audio, and behavioral data.
- Collaborate with model, application, and platform teams to productionize memory capabilities and optimize quality, latency, cost, reliability, and safety.
- Research AI infrastructure topics including fault localization, storage acceleration, heterogeneous resource scheduling, vector retrieval, and AI-agent-based infrastructure optimization.
Requirements
- Currently completing or recently completed a PhD in Software Development, Computer Science, Computer Engineering, Artificial Intelligence, or a related technical discipline.
- Strong experience in distributed systems, databases, information retrieval systems, or AI infrastructure, with proven system design and production engineering capabilities.
- Proficiency in at least one of Go, Python, or C++.
- Understanding of LLM application technologies including embeddings, retrieval-augmented generation, context engineering, retrieval systems, and long-term state management.
- Familiarity with memory extraction and representation, vector or graph indexing, retrieval and ranking, memory updating, compression and forgetting, or multimodal memory fusion.
- Preferred experience includes agent memory systems, user profiling, recommendation or search platforms, knowledge bases, multimodal processing, online inference, personalized agents, or long-term user state modeling.
- Preferred qualifications include work with memory frameworks such as mem0, memOS, or memU, and a strong record of publications, open-source contributions, or notable technical achievements.
- Ability to analyze system and algorithm trade-offs involving performance, latency, cost, scalability, and complex production systems.
- Ability to commit to an onboarding date by the end of 2027 and clearly state availability and graduation date.
Benefits
- The role is part of a 2027 global frontier technology recruitment program with an onboarding date by the end of 2027.
Categories
About ByteDance
ByteDance is a global incubator of platforms at the cutting edge of commerce, content, entertainment and enterprise services - over 2.5bn people interact with ByteDance products including TikTok. Creation is the core of ByteDance's purpose. Our products are built to help imaginations thrive. This is doubly true of the teams that make our innovations possible. Together, we inspire creativity and enrich life - a mission we aim towards achieving every day. At ByteDance, we create together and grow together. That's how we drive impact - for ourselves, our company, and the users we serve. We are committed to building a safe, healthy and positive online environment for all our users. We have over 110,000 employees based in more than 30 countries globally. Join us.