Careers · Engineering
AI Platform Engineer
Build the agent runtime, model routing, and orchestration layer that runs thousands of workflows in parallel.
What you’ll do
- Design and operate the multi-agent runtime and model-routing layer.
- Integrate model providers (Anthropic, OpenAI, Google, Mistral) behind a clean abstraction.
- Build evaluation and guardrail tooling for agent reliability.
- Optimize cost and latency across the inference pipeline.
What we’re looking for
- Experience building LLM-powered systems in production.
- Strong fundamentals in distributed systems and APIs.
- Familiarity with MCP, tool use, and RAG patterns is a plus.
- Pragmatic about reliability, cost, and evaluation.