AI Agent Engineer (Coding Agent)

Sekai

1d•Remote

About The Position

Sekai is building the TikTok for mini apps — an AI-driven consumer platform where people create, remix, share, and play interactive content instantly. We are a Series A company backed by Khosla, a16z, Mayfield, and A, with $30M raised to date. We are remote-first across all positions and are looking for ambitious, AI-native builders who want to help shape the next generation of consumer social products. We are doubling down on creation quality and reliability. This is a key role with real ownership: the person will run the lane end-to-end and set the technical bar for agent-driven app generation.

Requirements

Experience building agentic systems involving tool use, orchestration, retry/repair loops, and context management
Comfortable working with modern agent frameworks, such as LangChain, LangGraph, Google ADK, Pi-mono, or Vercel AI SDK
Strong engineers in Python or TypeScript
Experience shipping and operating production systems
Strong product instincts and can translate user experience goals into system design decisions

Nice To Haves

Built a coding agent, devtool, IDE assistant, or code generation pipeline
Experience building evaluation frameworks (automated scoring, regression suites, release gating)
Experience designing MCP-style tool protocols or robust tool interfaces for LLM systems

Responsibilities

Designing and owning the agent runtime and orchestration layer
Building long-horizon agent workflows: prompt → plan → generate → run/validate → repair → publish
Developing robust evaluation and quality loops including eval harnesses, regression testing, and failure taxonomy
Designing model strategies including routing, benchmarking, reliability improvements, and cost/latency optimization
Creating debuggable agent systems with tracing, metrics, alerts, and observability