Overview
Agent Infrastructure Engineer to own Superagent, a core agent harness that powers conversations, tool calls, and multi-step agentic workflows across AI products.
What you'll do
- Own Superagent’s architecture, development, and ongoing evolution.
- Design and optimize the agent execution loop for latency, reliability, token efficiency, cost, and task completion.
- Build core harness systems for context management, memory/state handling, and tool routing.
- Develop agent evaluation infrastructure to measure quality and guide engineering decisions.
- Integrate and benchmark multiple LLM providers and models for performance, cost, reliability, and capabilities.
- Implement observability and instrumentation (tracing, logging, metrics, regression detection) across agent runs.
- Debug complex issues across non-deterministic, distributed, model-driven systems.
What you'll need
- 4+ years of software engineering, backend engineering, or systems infrastructure experience.
- Strong proficiency in Python and/or TypeScript.
- Hands-on production experience building or operating LLM-based agents.
- Strong understanding of tool calling, function schemas, context limits, structured outputs, and unreliable LLM behavior.
- Experience with at least one agent framework (LangGraph, OpenAI Agents SDK, CrewAI, AutoGen, or custom).
- Experience building or working with evaluation suites/benchmarks or other measurement systems.
- Strong understanding of concurrency, caching, profiling, and performance optimization with latency/cost tradeoffs.
Nice to have
- Contributions to open-source agent frameworks, LLM tooling, or AI infrastructure.
- Experience with RAG pipelines, vector databases, or long-term memory systems for AI agents.
- Familiarity with MCP (Model Context Protocol) or similar tool-integration standards.
- Experience with LLM inference infrastructure (routing, rate limits, fallbacks, high-volume APIs).
- Experience with observability, distributed tracing, and production reliability.
- Experience with Kubernetes, Docker, cloud infrastructure, or distributed systems.
Details
Read the full description and apply on the company’s own careers page.
