AI Scientist – Knowledge Graphs & Memory Systems

About us: Axiomatic AI is building a new class of AI systems designed to reason with the rigor of the scientific method. By combining deep learning with formal logic and physics-based modeling, we create verifiable, interpretable AI systems that collaborate with and support human researchers in high-stakes scientific and engineering workflows.  Our mission, 30×30, is to deliver a 30× improvement in the speed, accessibility, and cost of semiconductor and photonic hardware development by 2030.  We aim to revolutionize hardware design and simulation in these industries and are building a team of highly motivated professionals to bring these innovations from research into commercial products. Position overview:  As an AI Scientist specializing in Knowledge Graphs and Memory Systems, you will lead the design and development of the knowledge layer that powers our agentic AI systems. You will build scalable, reliable approaches to representing and retrieving external scientific information such as papers, technical documentation, and structured data, as well as long-term memory of past system behavior, experiments, and outcomes. This role requires both scientific depth and strong hands-on engineering skills. You will stay close to state-of-the-art research in retrieval, knowledge representation, and memory for LLM-based systems, while also writing high-quality code to deliver working prototypes and robust components. Your mission: Research & Innovation: Lead and contribute to research on knowledge graphs, retrieval, and memory systems for agentic AI, staying current with the state of the art and identifying directions with high scientific and product impact. System Design & Implementation : Design and build core components for knowledge ingestion, representation, indexing, retrieval, and long-term memory, with a focus on scalability, robustness, and maintainability. Experiments & Evaluation : Design and run controlled experiments to evaluate retrieval and memory quality, define metrics and benchmarks, analyze failure modes, and iterate on methods to improve performance over time. Integration & Deployment : Work closely with engineers and scientists to integrate these components into agentic workflows and ensure they can be reliably used in real research and production settings. Analysis & Communication: Analyze experimental results and system behaviors, document findings in technical reports, and clearly communicate insights and trade-offs to both internal teams and external scientific stakeholders. Research Dissemination: Contribute to cutting-edge research in retrieval, knowledge representation, and memory systems, and publish results in leading AI venues when opportunities arise. Key requirements: PhD in Artificial Intelligence, Machine Learning, Computer Science, or a closely related field 2+ years of experience in AI research or applied research engineering, with a strong record of technical contributions Hands-on experience designing and building retrieval systems for LLM-based applications or agentic workflows Deep knowledge of retrieval and knowledge representation methods, including knowledge graphs, embedding-based retrieval, and hybrid approaches Proficiency in Python, with the ability to write clean, reliable code for research experiments and proof-of-concepts. Experience designing rigorous experiments and evaluation methodologies, including metrics, benchmarks, and failure mode analysis Strong collaboration skills, with the ability to discuss, develop, and refine ideas closely with a cross-functional team. Ability to guide junior team members and drive technical direction within a cross-functional team Ability to communicate complex technical ideas clearly through documentation, reports, and presentations Comfort working in a fast-paced research environment, navigating ambiguity, and iterating quickly based on evidence and results   Nice to have: Experience with graph databases and knowledge graph tooling (e.g., Neo4j) Familiarity with retrieval and indexing systems (e.g., Elasticsearch/OpenSearch, FAISS, vector databases) and hybrid search architectures Experience with RAG systems, document ingestion pipelines, and long-context retrieval strategies Experience building long-term memory systems for agents, including summarization, episodic/semantic memory, or memory consolidation techniques Familiarity with evaluation methods for retrieval and memory, including offline benchmarks and human-in-the-loop assessment Publications in relevant venues, or equivalent evidence of research impact (e.g., industrial research, open-source, patents) Experience collaborating with or supporting scientific/engineering teams using knowledge-intensive workflows   What we offer: Competitive compensation Stock Options Plan: Empowering you to share in our success and growth. Cutting-Edge Tools: Access to state-of-the-art tools and collaborative opportunities w