AI Engineer 6 - AI Foundation & Tooling, Ads Platform

Netflix Netflix · Big Tech · United States · Remote · Data & Insights

Staff AI Engineer to build AI infrastructure and agentic workflows for software development lifecycle at Netflix Ads Platform. This greenfield role focuses on applied AI, leveraging LLMs, agentic frameworks, and RAG to solve infrastructure and product problems, aiming for AI-native engineering.

What you'd actually do

  1. Architect and build a centralized context layer that gives AI agents grounded, team-specific knowledge
  2. Design and implement agentic workflows for the full development lifecycle: AI-assisted code generation, automated test creation, PR pre-review, and deployment validation
  3. Build AI-powered operational workflows — automated incident triage, log and metric correlation, root cause analysis, and guided resolution
  4. Develop multi-agent orchestration where parallel agents handle implementation, testing, and documentation as coordinated workflows
  5. Set up standardized AI development environments so every engineer can work in an AI-first workflow from day one

Skills

Required

  • 3+ years of significant focus on applied AI systems
  • Proven experience building and deploying agentic AI systems in production — agent architectures, tool integration, orchestration, and evaluation frameworks
  • Hands-on experience setting up AI infrastructure for end-to-end software development workflows (AI coding assistants, context engineering, automated testing)
  • Strong software engineering fundamentals — you build production-grade systems, not just prototypes
  • Deep experience with retrieval-augmented generation — document indexing, embedding strategies, retrieval pipelines, and grounding techniques
  • Proficiency in Python and/or JVM languages
  • Demonstrated ability to drive technical adoption across a team — you can demonstrate value, build trust through pairing and architecture reviews, and bring engineers along on new workflows

Nice to have

  • Prior experience as the first or early AI engineer on a team — standing up AI capabilities where none previously existed, with the ownership and initiative of an early-stage environment
  • Familiarity with LLM application patterns: context engineering, tool use / function calling, structured outputs, multi-agent coordination, and evaluation / hill-climbing methodologies
  • Experience integrating AI into CI/CD pipelines (automated PR review, test generation, deployment validation)
  • Background in building operational tooling — incident response automation, log analysis, diagnostic workflows

What the JD emphasized

  • first dedicated AI engineer
  • designing and building them from scratch
  • deep hands-on experience to architect the foundational layer
  • shipping faster without accumulating slop, regressions, or accountability gaps
  • building and deploying agentic AI systems in production
  • Hands-on experience setting up AI infrastructure for end-to-end software development workflows
  • strong software engineering fundamentals — you build production-grade systems, not just prototypes
  • Deep experience with retrieval-augmented generation

Other signals

  • building foundational AI infrastructure
  • designing and building AI systems from scratch
  • leveraging LLMs, agentic frameworks, and RAG
  • applied AI for infrastructure and product problems
  • AI-native engineering