Senior Staff AI Engineer, AI Agent Platform

What you'll do

• Design core agent loops including planning, reasoning, tool selection, memory, and error recovery as reusable patterns.
• Develop context engineering strategies for prompt architecture, window management, summarization, and RAG integration.
• Define tool connections and server patterns using the Model Context Protocol (MCP) for reliable agent usage.
• Design evaluation methodologies using task-level metrics, golden datasets, and LLM-as-judge graders.
• Build an evaluation harness to run offline benchmarks, simulated environments, and online quality monitoring.
• Run experiments on prompts, architectures, and models to iterate until agent quality meets production standards.
• Analyze traces and evaluation results to diagnose failure modes and form measurable hypotheses.
• Set the technical direction for agent design and mentor engineers on GenAI engineering practices.

What we're looking for

• 10+ years of experience in software engineering, ML engineering, or applied science with strong Python proficiency.
• Experience owning the design and delivery of significant systems involving multiple engineers or teams.
• Hands-on experience building GenAI applications and agentic systems with LLMs like GPT, Claude, Llama, or Qwen in production.
• Demonstrated experience designing and running experiments to improve LLM or agent performance, including defining metrics and building evaluation sets.
• Deep practical understanding of prompt/context engineering, tool calling, RAG, and agent architectures, including hands-on experience with MCP.
• Solid distributed systems fundamentals including concurrency, fault tolerance, latency, throughput tradeoffs, and API design for production services at scale.
• Demonstrated technical leadership influencing direction across teams.
• Experience building evaluation frameworks, using agent frameworks (e.g., LangGraph), or working with cloud AI platforms (preferred).