<p>Must-Have Requirements</p> <p>Requirement Details</p> <p>Backend/Systems Experience</p> <p>3+ years building production backend or distributed systems (pre-AI experience required)</p> <p>Production AI Systems</p> <p>Has shipped AI/LLM features serving real users at scale - not just prototypes or demos</p> <p>Agentic Systems</p> <p>Has built AI agents, skills, tools, or MCP (Model Context Protocol) integrations</p> <p>Python</p> <p>Proficient for backend development</p> <p>Secondary Language</p> <p>Working knowledge of Go, TypeScript, or Rust</p> <p>Cloud Infrastructure</p> <p>Deep experience with AWS/GCP/Azure - cost optimization, compute decisions, not just deployment</p> <p>Container & Orchestration</p> <p>Hands-on with Docker and Kubernetes - can build, deploy, debug, and scale services themselves</p> <p>LLM Integration</p> <p>Understands token economics, context limits, rate limiting, structured outputs, API failure modes</p> <p>LLM Evaluation</p> <p>Understands how to evaluate LLM outputs and the inherent challenges (non-determinism, quality measurement, regression detection)</p> <p>Hands-On Engineer</p> <p>Not just an architect - writes code, debugs production issues, deploys their own work</p> <p><strong><strong><strong><strong><strong><strong><strong><strong><strong>____</strong></strong></strong></strong></strong></strong></strong></strong></strong></p> <p>Preferred / Differentiators</p> <ul> <li>Built multi-step agentic workflows with tool use and function calling </li><li>Experience with agent orchestration frameworks (LangGraph, CrewAI, Claude Agent SDK, Google ADK, OpenAI ADK) </li><li>Built guardrails, fallbacks, or graceful degradation for AI systems </li><li>Streaming inference and async agent orchestration </li><li>Cost/latency optimization: caching, batching, prompt compression </li><li>ML observability tools: Langfuse, Arize, Braintrust, W&B </li><li>Retrieval systems (vector search, hybrid search) - as a tool, not the focus </li></ul> <p><strong><strong><strong><strong><strong><strong><strong><strong><strong>____</strong></strong></strong></strong></strong></strong></strong></strong></strong></p> <p>Screening Questions for Candidates</p> <ol> <li> <p>"Describe a production AI agent or skill system you built. What broke and how did you fix it?"</p> </li><li> <p>"Have you built MCP servers/integrations or custom tool-use systems for LLMs?"</p> </li><li> <p>"How do you evaluate whether an LLM-based feature is working well? What makes this hard?"</p> </li><li> <p>"Walk me through how you'd deploy and scale an AI service on Kubernetes."</p> </li></ol> <p><strong><strong><strong><strong><strong><strong><strong><strong><strong>____</strong></strong></strong></strong></strong></strong></strong></strong></strong></p> <p>Not a Fit If</p> <ul> <li>Primarily a model trainer/fine-tuner (we're not training models) </li><li>AI experience is mainly academic, research, or tutorial-based </li><li>No production systems experience (only notebooks/demos) </li><li>Looking for entry-level role with heavy mentorship </li><li>Background is primarily data science/analytics rather than engineering </li><li>"Architects" who don't write or deploy code themselves </li></ul> <p>Location : Cupertino,CA</p> <p>Salary Range: $95,000-$155,000 a year</p>