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