onsite
Applied Researcher I - Multi agent Systems & Knowledge Graphs - Capital One
Software Engineer
Conduct applied research on multi‑agent architectures and knowledge‑graph techniques such as GraphRAG and Graph‑of‑Thought, building trustworthy AI solutions for real‑time banking experiences.
About the role
Key Responsibilities
- Design, implement, and evaluate multi‑agent systems that integrate knowledge‑graph reasoning for banking use cases.
- Develop and fine‑tune GraphRAG and Graph‑of‑Thought pipelines, leveraging LangGraph and custom agent protocols.
- Collaborate with data scientists and engineers to embed trustworthy AI models into production services.
- Publish research findings, contribute to internal white‑papers, and present results to cross‑functional teams.
- Stay current with state‑of‑the‑art advances in generative AI, reinforcement learning, and graph‑based AI, applying them to solve business problems.
Requirements
- Strong programming skills in Python and experience with ML frameworks (e.g., PyTorch, TensorFlow).
- Hands‑on experience building or researching multi‑agent systems, knowledge graphs, or graph‑based retrieval‑augmented generation.
- Solid understanding of machine‑learning fundamentals, model evaluation, and AI safety principles.
- Track record of research contributions—publications, patents, or open‑source projects—in relevant domains.
- Excellent problem‑solving abilities and the capacity to work collaboratively in an agile, interdisciplinary environment.
Skills
pythonmachine learning