Research Scientist - AI Agent Memory Infrastructure - Global Frontier Tech Recruitment Program [...]

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

Responsibilities

We are looking for talented individuals to join our team in 2027. As a graduate, you will get opportunities to pursue bold ideas, tackle complex challenges, and unlock limitless growth. Launch your career where inspiration is infinite at our Company.

Successful candidates must be able to commit to an onboarding date by end of year 2027. Please state your availability and graduation date clearly in your resume.

Team Introduction

Join ByteDance’s AI Agent Memory Infrastructure team, where we build the core memory systems that power next‑generation intelligent agents. Our focus is on creating a unified platform for long‑term, conversational, and task‑oriented memory, enabling more personalized and context‑aware AI experiences.

We design and operate large‑scale, low‑latency, and highly reliable memory infrastructure, covering the full lifecycle from storage and retrieval to updating and optimization. Working at the intersection of LLMs, data systems, and context engineering, we tackle challenges in memory representation, retrieval, and multimodal fusion.

Partnering closely with model and product teams, we turn advanced research into scalable production systems that support a wide range of AI‑driven applications.

Responsibilities

• 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.
• Stay up‑to‑date with cutting‑edge advancements and contribute to the long‑term technical roadmap of AI agent memory systems, driving innovation and capability evolution.

Topic Content

With the large‑scale adoption of LLMs and AI agents, traditional cloud‑native infrastructure can no longer meet the ultra‑high performance and elasticity requirements of AI workloads. This topic conducts systematic research across the entire AI infrastructure stack:

• Network and Observability: Research intelligent fault localization and root cause analysis for large‑scale AI clusters, combined with intelligent tuning of time‑series databases to improve cluster stability.
• Storage Systems: Develop serverless high‑performance elastic file systems and storage acceleration architectures specifically for AI scenarios, explore hardware‑software co‑optimization for DPU, and overcome AI storage performance bottlenecks.
• Data Center Power Scheduling: Research GPU/CPU/MEM heterogeneous collaborative scheduling technologies, build a heterogeneous power orchestration system for AI agents, and address scheduling challenges including heterogeneous workloads and state dependencies.
• Vector Retrieval: Optimize core vector retrieval technologies for LLM‑powered applications, building a cloud‑native distributed vector index engine to meet ultra‑large‑scale vector retrieval demands with low latency and low cost.
• Intelligence and Agent Architecture: Explore automatic infrastructure optimization based on AI Agent workflows, build a self‑evolvable business agent framework, and enable full‑stack intelligent optimization through AI for Infra.

This topic aims to build a next‑generation AI‑native infrastructure to support the deployment of LLMs and AI agents, improve resource utilization, reduce costs, support elastic scaling, and drive the technological evolution of AI infrastructure.

Qualifications

Minimum Qualifications:

• Individuals who are 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.
• Proficient in at least one programming language such as Go, Python, or C++, with strong coding standards and engineering best practices.
• Solid understanding of core technologies in LLM applications, including but not limited to embeddings, retrieval‑augmented generation (RAG), context engineering, retrieval systems, and long‑term state management.
• Familiarity with one or more key areas in memory systems: memory extraction and representation, vector/graph indexing, retrieval and ranking, memory updating, compression and forgetting, multimodal memory fusion.

Preferred Qualifications

• Experience in agent memory systems, user profiling, recommendation/search feature platforms, or knowledge base systems.
• Contributions to or deep understanding of open‑source memory frameworks such as mem0, memOS, memU, or similar solutions.
• Strong track record in databases, information retrieval, machine learning, or AI systems, including publications, impactful open‑source work, or notable technical achievements.
• Experience in multimodal data processing, online inference systems, personalized agents, or long‑term user state modeling.
• Ability to analyze and optimize trade‑offs across system performance, latency, cost, and scalability from both system and algorithm perspectives; experience with complex production systems is highly preferred.

Job Information

Pay Transparency

The base salary range for this position in the selected city is $212,800 - $387,600 annually.

Compensation may vary outside of this range depending on a number of factors, including a candidate’s qualifications, skills, competencies and experience, and location. Base pay is one part of the Total Package that is provided to compensate and recognize employees for their work, and this role may be eligible for additional discretionary bonuses/incentives, and restricted stock units.

Benefits may vary depending on the nature of employment and the country work location. Employees have day one access to medical, dental, and vision insurance, a 401(k) savings plan with company match, paid parental leave, short‑term and long‑term disability coverage, life insurance, wellbeing benefits, among others. Employees also receive 10 paid holidays per year, 10 paid sick days per year and 17 days of Paid Personal Time (prorated upon hire with increasing accruals by tenure).

The Company reserves the right to modify or change these benefits programs at any time, with or without notice.

For Los Angeles County (unincorporated) Candidates

• Interacting and occasionally having unsupervised contact with internal/external clients and/or colleagues;
• Appropriately handling and managing confidential information including proprietary and trade secret information and access to information technology systems; and
• Exercising sound judgment.