About the Opportunity
We are seeking an AI Infrastructure Engineer to design and build the foundational systems that power next-generation AI agents. This role sits at the intersection of research and production engineering, focusing on scalable long-term memory, knowledge graph infrastructure, and robust context management systems.
You will transform cutting-edge research concepts (e.g., Context Graphs, GraphRAG, agent memory architectures) into auditable, maintainable, and production-grade infrastructure that enables reliable, stateful AI systems.
What You’ll Be Doing
- Architect and implement long-term memory infrastructure for AI agents, including auditable, versioned, and rollback-capable middleware that supports persistent, stateful reasoning.
- Design and own end-to-end GraphRAG and knowledge graph pipelines, from ingestion and schema design to graph indexing, retrieval optimization, and integration with LLM-based reasoning systems.
- Build scalable context management infrastructure, elevating context from prompt-level techniques to structured, maintainable systems such as Context Graphs that enable long-horizon and cross-session reasoning.
- Translate advanced agent research into production-grade systems, prototyping emerging architectures and establishing best practices for memory, retrieval, and infrastructure reliability.
- Ensure reliability, observability, and governance of agent infrastructure, including traceable memory operations, evaluation frameworks, and safeguards against drift and degradation.
What We Look For In You
- PhD or Master's in Computer Science, AI, Machine Learning, Robotics or related field with at least 10 years of industry experience.
- Possess a deep expertise in at least one of the following areas: long-term memory, knowledge graphs, or context management.
Nice to Haves
- Experience in top-tier AI labs or Tech industry leaders
- Experience in high-frequency trading, fintech, Web3, or crypto platforms is a strong advantage
- Startups or research-intensive environments preferred; must be comfortable operating with ambiguity and speed