Back to jobs

AI Scientist – Knowledge Graphs & Memory Systems

Barcelona, Spain

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 with leading experts in artificial intelligence, physics, hardware and electronic design automation.
  • Professional Growth: Opportunities to attend industry conferences, present research findings, and engage with the global AI research community.
  • Impact-Driven Culture: Join a passionate team focused on solving some of the most challenging problems at the intersection of AI and hardware.


Work model & location expectations:

  • Team work model: Hybrid
  • On-site expectations: 2/3 days per week
  • Primary location: Carrer d'Esteve Terradas 1, Castelldefels, Barcelona, Spain

Why join us? 

At Axiomatic_AI, you will be working on technology that drives innovation in AI for scientific and engineering applications in line with our 30 x 30 mission. This is your opportunity to contribute to the development of new AI architectures that can reason coherently and produce interpretable and verifiable solutions. Consequently, see those ideas commercialized into products that will shape the future of hardware and computing, while collaborating with a global team of engineers and AI specialists. We believe in pushing the boundaries of what is possible and continuously seek to redefine the intersection of AI, with focus on formal consistency. If you're ready to take your expertise in artificial intelligence and physics to the next level, we want to hear from you!

Worried about not meeting every qualification? Studies show that women and people of color are less likely to apply for jobs unless they meet every listed requirement. At Axiomatic-AI, we are dedicated to creating a diverse, inclusive, and authentic workplace. If this role excites you but your background doesn’t perfectly match every qualification, we still encourage you to apply. You could be the perfect fit for this position or another opportunity with us.

Apply for this job

*

indicates a required field

Resume/CV*

Accepted file types: pdf, doc, docx, txt, rtf

Cover Letter

Accepted file types: pdf, doc, docx, txt, rtf

Education

Select...
Select...
Select...
Select...
What is your preferred office location? *
Select...
Select...
Select...

Voluntary Self-Identification

For government reporting purposes, we ask candidates to respond to the below self-identification survey. Completion of the form is entirely voluntary. Whatever your decision, it will not be considered in the hiring process or thereafter. Any information that you do provide will be recorded and maintained in a confidential file.

As set forth in Axiomatic_AI’s Equal Employment Opportunity policy, we do not discriminate on the basis of any protected group status under any applicable law.

Select...
Select...
Race & Ethnicity Definitions

If you believe you belong to any of the categories of protected veterans listed below, please indicate by making the appropriate selection. As a government contractor subject to the Vietnam Era Veterans Readjustment Assistance Act (VEVRAA), we request this information in order to measure the effectiveness of the outreach and positive recruitment efforts we undertake pursuant to VEVRAA. Classification of protected categories is as follows:

A "disabled veteran" is one of the following: a veteran of the U.S. military, ground, naval or air service who is entitled to compensation (or who but for the receipt of military retired pay would be entitled to compensation) under laws administered by the Secretary of Veterans Affairs; or a person who was discharged or released from active duty because of a service-connected disability.

A "recently separated veteran" means any veteran during the three-year period beginning on the date of such veteran's discharge or release from active duty in the U.S. military, ground, naval, or air service.

An "active duty wartime or campaign badge veteran" means a veteran who served on active duty in the U.S. military, ground, naval or air service during a war, or in a campaign or expedition for which a campaign badge has been authorized under the laws administered by the Department of Defense.

An "Armed forces service medal veteran" means a veteran who, while serving on active duty in the U.S. military, ground, naval or air service, participated in a United States military operation for which an Armed Forces service medal was awarded pursuant to Executive Order 12985.

Select...

Voluntary Self-Identification of Disability

Form CC-305
Page 1 of 1
OMB Control Number 1250-0005
Expires 04/30/2026

Why are you being asked to complete this form?

We are a federal contractor or subcontractor. The law requires us to provide equal employment opportunity to qualified people with disabilities. We have a goal of having at least 7% of our workers as people with disabilities. The law says we must measure our progress towards this goal. To do this, we must ask applicants and employees if they have a disability or have ever had one. People can become disabled, so we need to ask this question at least every five years.

Completing this form is voluntary, and we hope that you will choose to do so. Your answer is confidential. No one who makes hiring decisions will see it. Your decision to complete the form and your answer will not harm you in any way. If you want to learn more about the law or this form, visit the U.S. Department of Labor’s Office of Federal Contract Compliance Programs (OFCCP) website at www.dol.gov/ofccp.

How do you know if you have a disability?

A disability is a condition that substantially limits one or more of your “major life activities.” If you have or have ever had such a condition, you are a person with a disability. Disabilities include, but are not limited to:

  • Alcohol or other substance use disorder (not currently using drugs illegally)
  • Autoimmune disorder, for example, lupus, fibromyalgia, rheumatoid arthritis, HIV/AIDS
  • Blind or low vision
  • Cancer (past or present)
  • Cardiovascular or heart disease
  • Celiac disease
  • Cerebral palsy
  • Deaf or serious difficulty hearing
  • Diabetes
  • Disfigurement, for example, disfigurement caused by burns, wounds, accidents, or congenital disorders
  • Epilepsy or other seizure disorder
  • Gastrointestinal disorders, for example, Crohn's Disease, irritable bowel syndrome
  • Intellectual or developmental disability
  • Mental health conditions, for example, depression, bipolar disorder, anxiety disorder, schizophrenia, PTSD
  • Missing limbs or partially missing limbs
  • Mobility impairment, benefiting from the use of a wheelchair, scooter, walker, leg brace(s) and/or other supports
  • Nervous system condition, for example, migraine headaches, Parkinson’s disease, multiple sclerosis (MS)
  • Neurodivergence, for example, attention-deficit/hyperactivity disorder (ADHD), autism spectrum disorder, dyslexia, dyspraxia, other learning disabilities
  • Partial or complete paralysis (any cause)
  • Pulmonary or respiratory conditions, for example, tuberculosis, asthma, emphysema
  • Short stature (dwarfism)
  • Traumatic brain injury
Select...

PUBLIC BURDEN STATEMENT: According to the Paperwork Reduction Act of 1995 no persons are required to respond to a collection of information unless such collection displays a valid OMB control number. This survey should take about 5 minutes to complete.