ByteDance

1 day ago

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

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI

Last checked: 23 hours agoStatus: Live

Job Summary

Build and evolve AI agent memory infrastructure that powers long-term, conversational, and task-oriented memory. Design low-latency, high-availability pipelines across storage, indexing, retrieval, updating, compression, and forgetting for real-time inference. Work on memory representation, retrieval/ranking, summarization and fusion, and multimodal workflows (text, image, audio, behavioral signals). Partner with model and product teams to productionize memory capabilities and optimize quality, latency, cost, reliability, and safety.

Location: San Jose

Workplace: Onsite

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Entry level

Key Responsibilities

•Design, build, and evolve next-generation memory infrastructure for AI agents with long-term, conversational, and task-oriented memory.
•Architect and optimize memory pipelines for large-scale, low-latency, high-availability environments spanning ingestion, storage, indexing, retrieval, updating, compression, and forgetting.
•Research challenges across LLMs, context engineering, and data management, including memory representation, retrieval/ranking, conflict resolution, summarization/fusion, and lifecycle management.
•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 continuously optimize performance across quality, latency, cost, reliability, and safety.

Key Requirements

•Completing or recently completed a PhD in Computer Science, Artificial Intelligence, Data Science, or related fields.
•Strong experience in distributed systems, databases, information retrieval systems, or AI infrastructure with proven system design and production engineering.
•Proficient 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 memory systems topics such as memory extraction/representation, vector/graph indexing, retrieval and ranking, memory updating, compression/forgetting, and multimodal memory fusion.

Experience:LLMAI infrastructureDistributed systemsInformation retrievalMultimodal

Education:PhD / Doctorate in Computer Science, Artificial Intelligence, Data Science, or related fields

Skills:System designProduction engineeringTrade-off analysisCollaborationRoadmap contribution

Tech Stack:GoPythonC++EmbeddingsRetrieval-augmented generation (RAG)Vector/graph indexingMultimodal fusion

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

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

ByteDance

1 day ago

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

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI

Last checked: 23 hours agoStatus: Live

Job Summary

Location: San Jose

Workplace: Onsite

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Entry level

Key Responsibilities

•Design, build, and evolve next-generation memory infrastructure for AI agents with long-term, conversational, and task-oriented memory.
•Architect and optimize memory pipelines for large-scale, low-latency, high-availability environments spanning ingestion, storage, indexing, retrieval, updating, compression, and forgetting.
•Research challenges across LLMs, context engineering, and data management, including memory representation, retrieval/ranking, conflict resolution, summarization/fusion, and lifecycle management.
•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 continuously optimize performance across quality, latency, cost, reliability, and safety.

Key Requirements

•Completing or recently completed a PhD in Computer Science, Artificial Intelligence, Data Science, or related fields.
•Strong experience in distributed systems, databases, information retrieval systems, or AI infrastructure with proven system design and production engineering.
•Proficient 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 memory systems topics such as memory extraction/representation, vector/graph indexing, retrieval and ranking, memory updating, compression/forgetting, and multimodal memory fusion.

Experience:LLMAI infrastructureDistributed systemsInformation retrievalMultimodal

Education:PhD / Doctorate in Computer Science, Artificial Intelligence, Data Science, or related fields

Skills:System designProduction engineeringTrade-off analysisCollaborationRoadmap contribution

Tech Stack:GoPythonC++EmbeddingsRetrieval-augmented generation (RAG)Vector/graph indexingMultimodal fusion

Company Brief

ByteDance

Industry: Digital Media

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Established Company

Headquarters: Beijing, China

Founded: 2012

Website LinkedIn