AI Agent Engineer (Coding Agent)

Sourced from feeny.ai

Sekai, a Series A consumer social startup backed by Khosla, a16z, and Mayfield, is hiring an AI Agent Engineer to own its coding-agent platform. You'll design the agent harness layer, build long-horizon autonomous workflows, and drive model strategy for agent-driven app generation. This is a remote-first, high-ownership role at the frontier of autonomous software generation.

• Design and own the agent harness layer
• Build long-horizon agentic workflows with maximal autonomy
• Develop evaluation and quality loops including eval harnesses, regression testing, and failure taxonomies
• Design model strategy: routing, benchmarking, reliability, and cost/latency optimization
• Create debuggable agent systems with tracing, metrics, alerts, and observability
• Research novel approaches and ship them to production

• Experience building agentic systems (tool use, orchestration, retry/repair loops, context management) on raw provider APIs or frameworks like LangGraph, PydanticAI, Google ADK, or Vercel AI SDK
• Experience with distributed / real-time systems
• Strong software engineering fundamentals with depth in Python and/or TypeScript
• Track record of shipping and operating production systems
• History of owning hard problems end to end
• Strong product instincts translating user-experience goals into system design

• Took a customer-facing product from 0 to 1
• Built a coding agent, devtool, IDE assistant, or code-generation pipeline
• Built evaluation frameworks (automated scoring, regression suites, release gating)
• Designed MCP-style tool protocols or robust tool interfaces for LLM systems
• Experience training and/or fine-tuning LLMs