Senior. Distinguished AI Engineer (agentic AI Platform)

Capital One Capital One · Banking · San Francisco, CA +4

This role is for a Senior. Distinguished AI Engineer on the Agentic AI Platform team at Capital One. The role focuses on building and scaling AI-powered products and platforms, with a strong emphasis on agent orchestration, RAG pipelines, and developer experience. The engineer will contribute to platform architecture, standardize agentic workflows, develop GenAI SDKs, implement trust and safety guardrails, optimize performance, and mentor other engineers. The role requires significant experience in AI/ML development, cloud platforms, and agentic frameworks.

What you'd actually do

  1. You will contribute to the north star platform architecture, continuously publishing and refining living diagrams and canonical APIs that cover agent orchestration, RAG pipelines, prompt libraries and multi-tenant policy enforcement.
  2. A major emphasis is around standardizing and automating agentic workflows : you will evaluate agentic frameworks such LangGraph, AutoGen, Semantic Kernal, CrewAI and LlamaIndex and then harden / blend patterns that best meet enterprise SLAs do that 90% of new apps adopt them.
  3. Developer experience is another cornerstone. You will contribute to crafting an end to end GenAI SDK, CLI and starter kits that let AI engineers spin up secure, observable agentic workflows in under minutes, shrinking prototyping to production timelines by 30%.
  4. Trust and safety remain paramount; you will help bring together a vision of central guardrail services - prompt firewalls, content-filter hooks, red team harnesses and audit APIs - consumed by every application to ensure zero Sev4 incidents.
  5. You’ll own central Helm charts, operators and CRDs that auto scale agents to hit tenant SLAs

Skills

Required

  • Python
  • Go
  • Scala
  • Java
  • developing AI and ML algorithms or technologies
  • deploying scalable and responsible AI solutions on cloud platforms
  • supporting Agentic Frameworks (LangChain, CrewAI, Semantic Kernel (Microsoft), or AutoGen)
  • LLMOps (Google Cloud Vertex AI, Amazon SageMaker, Azure Machine Learning)
  • designing mission-critical machine learning platforms
  • architecting, designing, developing, integrating, delivering, and supporting complex AI systems
  • leading and mentoring multiple engineering teams
  • influencing cross-functional stakeholders up to the VP level
  • LLM Inference
  • Similarity Search and VectorDBs
  • Guardrails
  • Memory

Nice to have

  • Computer Science
  • Engineering
  • AI
  • C++
  • C#
  • Golang

What the JD emphasized

  • delivering AI-powered products
  • agent orchestration
  • RAG pipelines
  • standardizing and automating agentic workflows
  • enterprise SLAs
  • GenAI SDK, CLI and starter kits
  • agentic workflows
  • central guardrail services
  • prompt firewalls
  • content-filter hooks
  • red team harnesses
  • audit APIs
  • zero Sev4 incidents
  • optimizing orchestration
  • hierarchical agent memory
  • multimodal guardrails
  • multimodal RAG
  • auto scale agents
  • tenant SLAs

Other signals

  • building and deploying proprietary solutions
  • advance the state of the art in science and AI engineering
  • build and deploy proprietary solutions that are central to our business
  • empower teams across Capital One to enhance their products with the transformative power of AI
  • deliver AI-powered products that change how our associates work and how our customers interact with Capital One
  • standardizing and automating agentic workflows
  • Developer experience is another cornerstone
  • crafting an end to end GenAI SDK, CLI and starter kits
  • Trust and safety remain paramount
  • central guardrail services
  • drive end to end performance by optimizing orchestration
  • accelerate innovation by incubating proof of concepts
  • own central Helm charts, operators and CRDs that auto scale agents to hit tenant SLAs
  • coach and evangelize
  • representing Capital One at Tier1 AI conferences