Research Scientist - AI Agent Memory Infrastructure - Global Frontier Tech Recruitment Program - 2027 Start (PhD)

ByteDance
San Jose
Workplace: OnsiteFull timeFunction: Data Science & Machine LearningEducation: phdSkills: ["System design","Production engineering","Coding standards","Trade-off analysis","Cross-team collaboration"]

Design and build next-generation memory infrastructure for AI agents, creating unified long-term, conversational, and task-oriented memory. Architect low-latency, high-availability pipelines across ingestion, storage, indexing, retrieval, updating, compression, and forgetting. Tackle challenges at the intersection of LLMs, context engineering, and data management, including multimodal memory fusion, and productionize capabilities with model, application, and platform teams.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
ByteDance
ByteDance
1 month ago

Research Scientist - AI Agent Memory Infrastructure - Global Frontier Tech Recruitment Program - 2027 Start (PhD)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 30 days agoStatus: Live
Reposted: similar role first listed 1 month ago

Job Summary

Design and build next-generation memory infrastructure for AI agents, creating unified long-term, conversational, and task-oriented memory. Architect low-latency, high-availability pipelines across ingestion, storage, indexing, retrieval, updating, compression, and forgetting. Tackle challenges at the intersection of LLMs, context engineering, and data management, including multimodal memory fusion, and productionize capabilities with model, application, and platform teams.
Location: San Jose
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Graduate level

Key Responsibilities

  • •Design, build, and evolve next-generation memory infrastructure for AI agents, supporting long-term, conversational, and task-oriented memory.
  • •Architect and optimize memory system pipelines for large-scale, low-latency, high-availability environments across ingestion, storage, indexing, retrieval, updating, compression, and forgetting.
  • •Research challenges in memory representation, retrieval and ranking, conflict resolution, summarization and fusion, and memory lifecycle management at the intersection of LLMs and context engineering.
  • •Design unified memory models and processing workflows for multimodal data (text, image, audio, behavioral signals) to improve consistency, personalization, and task completion.
  • •Collaborate with model, application, and platform teams to productionize memory capabilities and optimize performance across quality, latency, cost, reliability, and safety.

Key Requirements

  • •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 programming language such as Go, Python, or C++ with strong coding standards.
  • •Solid understanding of core LLM application technologies, including embeddings, retrieval-augmented generation (RAG), context engineering, retrieval systems, and long-term state management.
  • •Familiarity with key memory-system areas such as memory representation, vector/graph indexing, retrieval and ranking, updating, compression/forgetting, and multimodal memory fusion.
Experience:AI infrastructureDistributed systemsLLM applicationsInformation retrievalMultimodal AI
Education:PhD / Doctorate in Software Development, Computer Science, Computer Engineering, Artificial Intelligence (or related)
Skills:System designProduction engineeringCoding standardsTrade-off analysisCross-team collaboration
Tech Stack:GoPythonC++LLMsEmbeddingsRetrieval-augmented generation (RAG)Context engineeringRetrieval systemsVector indexingGraph indexingMultimodal data fusionStorage systemsServerlessTime-series databasesVector retrievalDistributed vector index engineFault localizationRoot cause analysisGPU/CPU/MEM schedulingDPU

Company Brief

ByteDance
Develops consumer internet and content platforms, including TikTok and other apps for short-form video, news, and entertainment. It also builds advertising, commerce, and creator tools that connect audiences, brands, and publishers across global markets.
Industry: Digital Media
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Established Company
Headquarters: Beijing, China
Founded: 2012
WebsiteLinkedIn