• Partner with a cross-functional team of engineers, research scientists, technical program managers, and product managers to deliver AI-powered products • Design, develop, test, deploy, and support AI software components including foundation model training, large language model inference, similarity search, guardrails, model evaluation, experimentation, governance, and observability • Leverage a broad stack of Open Source and SaaS AI technologies such as AWS Ultraclusters, Huggingface, VectorDBs, Nemo Guardrails, PyTorch, and more • Invent and introduce state-of-the-art LLM optimization techniques to improve the performance — scalability, cost, latency, throughput — of large scale production AI systems • Contribute to the technical vision and the long term roadmap of foundational AI systems at Capital One

• Build AI-Enabled Products: Develop products that are fully enabled by the capabilities of LLMs and other recent developments in foundation models. You will evaluate and assimilate emerging techniques into our production systems. • High-Performance Search and RAG: Build and optimize our data indexing, ranking, and query processing systems for high-performance Search and Retrieval-Augmented Generation (RAG). • Develop Evaluation Frameworks: Create robust frameworks to evaluate the performance of our agents, RAG systems, and various LLMs. We take a polyglot approach to working with LLMs, with a strong preference for getting workloads running on open-source models.

• Diseñar y desarrollar modelos de ML para soluciones de ingeniería de alto impacto • Recopilación y preprocesamiento de datos estructurados y no estructurados • Identificación, extracción y transformación de características relevantes • Evaluación de la precisión y robustez del modelo • Implementación y integración de soluciones en la nube • Investigación e innovación en tecnologías de IA/ML • Preparación de documentación exhaustiva sobre arquitectura de modelos y métricas de evaluación

• Design and Deploy Production AI Agentic Systems: Architect, build, and deploy autonomous AI agents using state-of-the-art frameworks like ADK (Agentic Design Kit) and LangGraph that leverage LLMs to automate code reviews, quality analysis, and development workflow optimization at scale • Architect Advanced Context Engineering Solutions: Design sophisticated context engineering strategies including dynamic context assembly, agentic retrieval patterns, memory systems (episodic and working memory), and multi-hop reasoning pipelines for complex code analysis tasks. • Develop AI-Powered Automation Tools: Build intelligent backend services in Python and Java that leverage GenAI to detect anti-patterns, suggest improvements, and standardize development workflows. • Establish AI-Enhanced Engineering Excellence: Define and implement coding standards and best practices specifically for GenAI systems, including LLM evaluation metrics, guardrails, and responsible AI principles. • Lead AI-Powered Code Reviews: Conduct comprehensive code reviews using state-of-the-art GenAI tools and agents, providing architectural guidance on performance, security, and AI system design. • Innovate with Emerging Technologies: Stay current with rapidly evolving GenAI technologies and integrate cutting-edge capabilities (function calling, tool use, fine-tuning, prompt caching) into production systems. • Mentor on AI Engineering: Coach engineers on GenAI best practices, AI agent design patterns, prompt engineering, and responsible AI development. • Collaborate Across Functions: Partner with product owners, architects, security teams, and stakeholders to ensure AI solutions align with quality standards and business objectives.