This is a Test Job Opening, Do not Apply to it. We're looking for a software developer to design and build autonomous AI agent systems — software that can plan, make decisions, and take multi-step actions with minimal human oversight. What you'll do Design, build, and maintain agentic workflows and AI-driven automation systems Integrate LLMs with tools, APIs, and external systems to enable autonomous task execution Develop and refine prompting strategies, memory systems, and orchestration logic for multi-agent pipelines Implement guardrails, evaluation frameworks, and monitoring to ensure agent reliability and safety Collaborate with product and engineering teams to identify high-value automation opportunities Debug and iterate on agent behavior using observability tools and structured testing What we're looking for Strong software engineering fundamentals (Python, TypeScript, or similar) Experience with LLM APIs (OpenAI, Anthropic, etc.) and agent frameworks (LangChain, LangGraph, CrewAI, or custom-built) Familiarity with tool-calling, RAG, and prompt engineering Understanding of distributed systems, async programming, and API design Comfort working in a fast-moving, experimental environment where best practices are still emerging Bonus: experience with evaluation/testing frameworks for non-deterministic systems