AI Agent Memory Systems Research Scientist

ByteDance; San Jose (CA); On-site; USD 212,800 - 387,600; Full time

Job summary

ByteDance’s AI Agent Memory Infrastructure team is seeking PhD-level talent to design and build unified memory systems powering long-term, conversational, and task-oriented AI agents. You will tackle memory representation, retrieval, and multimodal fusion at scale in a fast-paced environment.

Collaborate with model, product, and platform teams to productionize memory capabilities, optimize latency and reliability, and contribute to the long-term roadmap of AI infrastructure.

Qualifications

• PhD completed or near completion in CS/AI/related field.
• Strong background in distributed systems, databases, or AI infrastructure.
• Proficiency in Go, Python, or C++ with solid engineering practices.
• Solid understanding of LLMs, embeddings, RAG, context engineering, long-term state management.
• Familiarity with memory systems: extraction, vector indexing, updating, and multimodal fusion.

Responsibilities

• Design and evolve next-generation memory infrastructure for AI agents (long-term, conversational, task-oriented).
• Architect and optimize pipelines for low latency, high availability (ingestion, storage, indexing, retrieval, updating, forgetting).
• Explore memory representation, ranking, and fusion across LLMs and data management.
• Develop unified memory models for multimodal data (text, image, audio, behavioral signals).
• Collaborate with model, application, and platform teams to productionize memory features and optimize performance, cost, reliability, and safety.
• Stay current with memory system advances and contribute to roadmap.

Skills

Go

Python

C++

Distributed systems

Information retrieval

LLM basics

Education

PhD in Software Development / CS / AI

Tools

mem0

memOS

memU

Job description

ByteDance’s AI Agent Memory Infrastructure team is seeking PhD-level talent to design and build unified memory systems powering long-term, conversational, and task-oriented AI agents. You will tackle memory representation, retrieval, and multimodal fusion at scale in a fast-paced environment.

Collaborate with model, product, and platform teams to productionize memory capabilities, optimize latency and reliability, and contribute to the long-term roadmap of AI infrastructure.