AI Agent Engineer (Coding Agent)
Sekai
Software Engineering, Data Science
United States
Posted on Mar 20, 2026
What is Sekai?
Sekai is building the TikTok for interactive mini-apps. Users scroll a feed of playable content—and they can also create new mini-apps (games, quizzes, interactive stories, utilities) simply by describing what they want.
Why we’re hiring
We’re 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.
Role: Senior AI Agent Engineer / Tech Lead (Coding Agent)
You will own
- 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
We’re looking for
- have more than 5 year full-time working experience
- Have experience building agentic systems involving tool use, orchestration, retry/repair loops, and context management
- Are comfortable working with modern agent frameworks, such as
- LangChain, LangGraph, Google ADK, Pi-mono, or Vercel AI SDK
- Are strong engineers in Python or TypeScript
- Have experience shipping and operating production systems
- Have strong product instincts and can translate user experience goals into system design decisions
Bonus points
- 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
Compensation & benefits
- Compensation: competitive base salary + equity
- Health coverage: we cover full health insurance