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

What you'll do

• Build and optimize memory pipelines for ingestion, storage, indexing, retrieval, updating, compression, and forgetting.
• Develop memory models and workflows involving LLMs, context engineering, retrieval, ranking, and multimodal data.
• Collaborate with model, application, and platform teams to deploy memory capabilities and improve quality, latency, cost, reliability, and safety.

What they ask for

• Completing or recently completed a PhD in Computer Science, Artificial Intelligence, Data Science, or a related field.
• Strong experience in distributed systems, databases, information retrieval systems, or AI infrastructure, with system design and production engineering capability.
• Proficiency in at least one of Go, Python, or C++; understanding of LLM application technologies such as embeddings, RAG, context engineering, retrieval systems, and long-term state management.
• Familiarity with at least one memory-system area, such as memory representation, vector/graph indexing, retrieval and ranking, updating, compression and forgetting, or multimodal fusion.

Nice to have

• Experience with 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, or memU; relevant publications or impactful technical work are also valued.

Tools

Go, Python, C++, LLMs, RAG, embeddings, vector/graph indexing

AI focus

Builds AI agent memory systems, including long-term, conversational, task-oriented, and multimodal memory, and productionizes them for personalized interactions.