Netflix
Software Engineer 5 – Agent Platform, AI Platform
About this role
At Netflix, our mission is to entertain the world. Together, we are writing the next episode - pushing the boundaries of storytelling, global fandom and making the unimaginable a reality. We are a dream team obsessed with the uncomfortable excitement of discovering what happens when you merge creativity, intuition and cutting-edge technology. Come be a part of what’s next. At Netflix, we want to entertain the world, and we're constantly innovating on how entertainment is imagined, created, and delivered to a global audience. Increasingly, that innovation is powered by AI — and Netflix is making a deliberate bet to become AI Native, with AI woven into how we build products, create content, and run the company. The Opportunity The Agent Platform team gives Netflix engineers the infrastructure to go from zero to a production-grade AI agent without reinventing the wheel. We own the foundational building blocks the whole company builds on: the Model Gateway (unified access to external LLMs like Claude, GPT, and Gemini), the Assistance API for conversational use cases, the MCP Gateway that connects agents to Netflix's internal systems and knowledge, our Agent SDK, and an end-to-end evaluation stack. The work has moved well beyond chat completions. Teams across Netflix are now building agents — systems that plan, call tools, observe results, and iterate — and they depend on us for the infrastructure to do that reliably and to know whether their agents are actually any good. We're a small team with outsized leverage: what we ship becomes the foundation for AI across all of Netflix. What you will do:
- Design, build, and operate the Agent SDK and MCP Gateway that Netflix engineers use to build, deploy, and run AI agents in production.
- Build agents and agent infrastructure across the full lifecycle — plan/act/observe loops, tool and MCP integrations, deployment, and day-2 operations.
- Make evaluation a first-class part of the platform: build the tracing, eval suites, and quality signals that let teams measure agents, catch regressions, and iterate to make them better.
- Own reliability, observability, and guardrails for non-deterministic systems running at very high scale
- Lead cross-functional initiatives with ML scientists, data scientists, product managers, and other AI Platform teams.
- Rapidly iterate with users to improve the developer experience while establishing durable foundational capabilities. Desired Background:
- 8+ years of software engineering experience with a track record of delivering quality results.
- Hands-on experience building, deploying, operating, AND evaluating LLM agents in production — not just chat-completion apps or prototypes.
- Experience with one or more agent frameworks/SDKs (Strands, OpenAI Agents SDK, Anthropic Claude Agent SDK, LangGraph, pydantic-ai, CrewAI, Google ADK) and with tool/function calling and MCP.
- Experience with LLM/agent evaluation and observability — building eval suites, tracing, and quality measurement, then iterating on results (Braintrust, LangSmith, W&B, or equivalent).