Principal AI Engineer

Job Description

Capital One is seeking a highly skilled Principal AI Engineer to accelerate the implementation and scaling of Agentic AI solutions. This is a hands-on engineering role focused on building production-grade AI systems that drive engineering and operational excellence. The ideal candidate combines deep Generative AI expertise, advanced Python development skills, and strong AWS cloud architecture experience. You will work within the People Tech organization alongside full-stack engineers, engineering leadership, and cross-functional stakeholders to design, develop, and deploy autonomous AI systems that solve complex business challenges. Key Responsibilities: Design and deploy multi-agent AI systems using frameworks such as LangGraph and CrewAI Build and optimize Retrieval-Augmented Generation (RAG) pipelines using Amazon Bedrock and vector databases Develop scalable FastAPI-based backend services supporting AI-powered applications Integrate AI solutions with enterprise platforms including ServiceNow, CMDB, and Jira Implement AI observability, monitoring, evaluation, and tracing frameworks Create responsible AI guardrails, content moderation, and prompt safety mechanisms Collaborate with frontend engineers on AI-enabled user experiences and streaming interfaces Establish CI/CD pipelines for AI applications, prompts, and model deployments Contribute to architecture decisions and mentor engineering teams on AI best practices Drive production readiness, scalability, reliability, and performance of AI systems Required Qualifications: 10+ years of software engineering experience 7+ years of professional Python backend development 2+ years of hands-on experience building applications with LLMs such as Claude, GPT, or Llama 5+ years of AWS cloud architecture and development experience Strong experience with LangChain, LangGraph, CrewAI, or similar orchestration frameworks Expertise in FastAPI, Pydantic, asynchronous programming, and API development Experience with Amazon Bedrock, SageMaker, Lambda, and cloud-native architectures Hands-on experience implementing RAG systems and vector databases Strong understanding of AI evaluation, observability, and monitoring frameworks Preferred Qualifications: Previous Capital One experience Experience with OpenSearch, Pinecone, pgvector, or similar vector databases Familiarity with LangSmith, OpenTelemetry, Ragas, and DeepEval Experience scaling AI solutions from proof of concept to enterprise production environments Knowledge of AI governance, compliance, and responsible AI practices

Responsibilities

• Design and deploy multi-agent AI systems using LangGraph, CrewAI, and related frameworks.
• Build and optimize production-grade RAG pipelines using Amazon Bedrock and vector databases.
• Develop scalable FastAPI backend services supporting AI-powered applications.
• Integrate AI solutions with enterprise platforms including ServiceNow, Jira, and CMDB.
• Implement AI observability, tracing, monitoring, and evaluation frameworks.
• Create responsible AI guardrails, prompt safety controls, and content moderation solutions.
• Collaborate with frontend teams to deliver AI-enabled user experiences.
• Establish CI/CD pipelines for AI models, prompts, and application deployments.
• Mentor engineers and contribute to AI architecture and engineering best practices.
• Drive production readiness, scalability, reliability, and performance of AI systems.

Benefits

• Competitive contract compensation.
• Hybrid work environment with collaboration across McLean and Richmond teams.
• Opportunity to build cutting-edge Agentic AI solutions at enterprise scale.
• Exposure to modern AI technologies including Claude, GPT, Llama, and Amazon Bedrock.
• Work alongside experienced engineering leaders and AI practitioners.
• Opportunity to influence the future direction of AI initiatives within Capital One.
• Access to large-scale production AI systems and real-world business applications.
• Professional growth through complex, high-impact AI engineering projects.