Sekai

AI Agent Engineer (Coding Agent)

Sekai
Apply
4 months ago
Remote, United StatesSenior

Responsibilities

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

Requirements

  • Experience building agentic systems involving tool use, orchestration, retry and repair loops, and context management.
  • Experience with distributed or real-time systems.
  • Strong software engineering fundamentals with depth in Python and/or TypeScript.
  • A track record of shipping and operating production systems.
  • Experience owning difficult problems end to end and demonstrating the systems built and outcomes achieved.
  • Strong product instincts and the ability to translate user-experience goals into system-design decisions.
  • Preferred experience includes taking a customer-facing product from zero to one, building coding agents or developer tools, creating code-generation pipelines, building evaluation frameworks, designing MCP-style tool protocols, and training or fine-tuning large language models.

Benefits

  • Remote-first work across all positions.
  • Full medical and health insurance coverage.
  • Salary and equity compensation are offered.
Sekai

About Sekai

11-50 employees
Contact me