AI Agent Engineer – Build Autonomous Coding Agents

About the role

Sekai is building an AI‑driven consumer platform for mini apps, enabling users to create, remix, share and play interactive content instantly. The team is looking for an AI Agent Engineer to own the end‑to‑end development of autonomous coding agents that generate high‑quality software quickly and tastefully.

Key responsibilities

• Design and own the agent harness layer that powers autonomous app generation.
• Build long‑horizon agentic workflows with maximal autonomy.
• Develop robust evaluation and quality loops, including regression testing and failure taxonomies.
• Design model strategy covering 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.

Required profile

• Experience building agentic systems with tool use, orchestration, retry/repair loops and context management.
• Background in distributed and real‑time systems.
• Research‑and‑ship mindset, treating open‑ended problems as experiments and delivering production results.
• Strong software engineering fundamentals with depth in Python and/or TypeScript.
• Proven track record of shipping and operating production systems end‑to‑end.

Required skills

• Python
• TypeScript
• LangGraph
• PydanticAI
• Google ADK
• Pi‑mono
• Vercel AI SDK
• Distributed systems
• Real‑time systems
• LLM fine‑tuning

What we offer

• Competitive compensation including salary and equity.
• Full medical and health insurance coverage.