AI Agent Systems Engineer

Sekai; San Francisco, Northern (CA, KY); Hybrid; USD 180,000 - 250,000; Full time

Benefits offered by this job

Competitive compensation: salary +equ

Full medical / health insurance

Job summary

Sekai is building the TikTok for mini apps—a fast-paced, AI-native consumer platform. We seek engineers who will own the end-to-end design of agent-driven app generation, focusing on systems-level thinking and reliable production deployment.

Responsibilities include building the agent harness layer, developing eval loops and testing, and designing model strategy for cost and latency. Remote-first, with ambitious, hands-on builders encouraged to apply.

Qualifications

• Experience building agentic systems with tool use, orchestration, retries and context management.
• Strong understanding of distributed / real-time systems.
• Research-and-ship mindset with production readiness in Python and/or TypeScript.
• Track record of shipping and operating production systems.
• Translate user goals into system-design decisions.

Responsibilities

• Designing and owning our agent harness layer and long-horizon workflows.
• Developing robust evaluation loops, including eval harnesses and testing.
• Designing model strategy for routing, benchmarking, reliability, cost and latency.

Skills

Agentic systems

Python

TypeScript

Distributed systems

Production systems

Product instincts

Education

Bachelor's degree in CS or related field

Tools

LangGraph

PydanticAI

Google ADK

Pi-mono

Vercel AI SDK

Job description

Sekai is building the TikTok for mini apps—a fast-paced, AI-native consumer platform. We seek engineers who will own the end-to-end design of agent-driven app generation, focusing on systems-level thinking and reliable production deployment.

Responsibilities include building the agent harness layer, developing eval loops and testing, and designing model strategy for cost and latency. Remote-first, with ambitious, hands-on builders encouraged to apply.