Full Stack Engineer 5 - Global Workforce Services - AI Automation

Capital One • Richmond, VA

20d

About The Position

Capital One is seeking a Full Stack Engineer to help transform Global Workforce Services, the engineering team supporting enterprise facilities and physical security across SaaS, COTS, and custom applications. The team supports a 10,000-plus-device IoT footprint and is modernizing IoT management and software delivery using AI, autonomous agents, and retrieval-augmented generation (RAG) pipelines.

The role leads a portfolio of technology projects and developers, provides technical leadership across teams, and drives the design and implementation of reliable, high-performance distributed and cloud-native systems. It includes architecting responsive web interfaces and real-time AI chat and agent interfaces; building high-throughput microservices and APIs; integrating AI agents with enterprise systems, databases, third-party APIs, and legacy software; and combining rule-based, retrieval-augmented, and generative AI components into production pipelines. The engineer partners with product managers, architects, and product leaders on cloud solutions, platform roadmaps, and shared-services strategy, while mentoring engineers and contributing to technology communities.

Requirements

• Bachelor's degree or higher in Computer Science or a related quantitative field, such as Statistics, Economics, Operations Research, Analytics, Mathematics, or Engineering.
• At least 6 years of software engineering experience; internship experience does not count toward this requirement.
• At least 3 years of experience with public cloud platforms (AWS, GCP, or Azure), cloud-based productivity tools, or virtualization technologies.

Nice To Haves

• Master's degree in Computer Science or a related field.
• 2 or more years of experience building production RAG pipelines, including chunking, embeddings, vector indexing, graph RAG, or fine-tuning.
• 2 or more years of experience with agentic patterns such as tool calling, ReAct loops, Plan-and-Execute, or multi-agent collaboration.
• 2 or more years of experience with LLM orchestration frameworks such as LangChain, LangGraph, LlamaIndex, or Semantic Kernel, and model APIs such as OpenAI, Anthropic, Bedrock, Ollama, or Hugging Face.
• 2 or more years of experience building agentic AI systems and workflows.
• 2 or more years of experience developing AI or ML algorithms or technologies—such as LLM inference, similarity search and vector databases, guardrails, or memory—using Python, C++, C#, Java, CUDA, or Golang.
• 2 or more years of experience right-sizing models, instance counts, and hardware types to requirements such as context length and token inputs and outputs.
• 9 or more years of coding experience with more than two of Go, Java, JavaScript/TypeScript, Python, Rust, C#, or Scala.
• 5 or more years of experience contributing to open-source frameworks.
• 5 or more years of experience with front-end JavaScript or TypeScript frameworks.
• 5 or more years of experience creating synchronous and asynchronous APIs.
• 4 or more years of experience with databases and database management systems.
• 4 or more years of experience with CI/CD pipelines, infrastructure as code, and automated testing frameworks.
• 4 or more years of experience using Git-based version-control systems such as Git, GitHub, or Bitbucket.
• 4 or more years of experience troubleshooting technical issues in cloud environments.
• 3 or more years of experience mentoring senior engineers and driving professional development within technical teams.
• 2 or more years of experience using observability to identify and optimize performance bottlenecks in distributed systems.
• 2 or more years of experience leading architectural design reviews and influencing enterprise-wide technical standards and methodologies.
• 1 or more years of experience establishing and enforcing coding standards and design patterns across teams.
• 1 or more years of experience implementing observability and reliability practices at scale.
• Experience influencing technology strategy at the portfolio or business-unit level.
• Experience leading cross-functional engineering efforts or large-scale technical initiatives.

Responsibilities

• Lead a portfolio of technology projects and a team of developers building distributed microservices and full-stack systems that address regulatory needs.
• Architect performant, responsive web interfaces and real-time streaming AI chat and agent interfaces using modern frameworks.
• Build resilient, high-throughput microservices and APIs, including support for Server-Sent Events and WebSockets for real-time AI responses.
• Integrate AI agent capabilities with enterprise systems, databases, third-party APIs, and legacy software using tool-calling and function-calling patterns.
• Architect and integrate rule-based, retrieval-augmented, and generative AI systems into unified production pipelines.
• Stay current with technology trends, experiment with new technologies, participate in technology communities, and mentor members of the engineering community.
• Collaborate with digital product managers to deliver robust cloud-based solutions.
• Provide technical leadership across multiple teams and shape system architecture and long-term technology direction.
• Lead end-to-end design and implementation of large-scale distributed or cloud-native systems with high reliability and performance requirements.
• Partner with architects and product leaders to define platform roadmaps and shared-services strategy.

Benefits

• Comprehensive, competitive health, financial, and other benefits supporting total well-being; eligibility varies by employment status and management level.
• Performance-based incentive compensation, which may include cash bonuses and/or long-term incentives.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior