AI Engineer (LLM / Agentic Systems)

<div style="box-sizing: border-box; color: rgb(51, 51, 51); text-align: center;"><strong style="box-sizing: border-box;"><span style="box-sizing: border-box; color: rgb(184, 49, 47);">Dear applicants, please keep in mind that applications without provided salary expectations and active LN profile will not be considered. Hope for your understanding.</span></strong></div><div><br></div><div><strong>Location: San Francisco, CA (On-site)<br>Employment Type: Full-Time<br>Benefits: 100% medical, dental, vision; MacBook Pro + peripherals</strong></div><div><br></div><div>We are hiring an AI Engineer to own the intelligence layer. This is not a demo or prototype role. This is production AI engineering.</div><div><br></div><div>About the Company</div><div>Client builds production AI agents that replace manual coordination work inside billion-dollar enterprises. Our agents operate at scale — processing thousands of transactions, making classification decisions, routing exceptions, and learning from human feedback.</div><div><br></div><div>We deploy intelligent agents directly into enterprise systems such as:</div><div>Salesforce</div><div>NetSuite</div><div>ServiceNow</div><div>Workday</div><div><br></div><div>You will:</div><div>Design and ship agentic systems used in real enterprise workflows</div><div>Build evaluation and reliability systems</div><div>Handle hallucinations, edge cases, cost constraints</div><div>Optimize multi-agent orchestration in production</div><div>You should already have built LLM-powered systems that operate beyond the playground stage.</div><div><br></div><div>What You’ll Own</div><div>Agent architecture design</div><div>Retrieval systems (RAG, context management)</div><div>Tool calling and multi-step reasoning</div><div>Multi-agent orchestration</div><div>Prompt engineering and reliability optimization</div><div>Evaluation and quality infrastructure</div><div>Cost-performance tradeoff optimization</div><div>Exception routing and human-in-the-loop feedback loops</div><div><br></div><div>Must-Have Requirements</div><div>3+ years software engineering experience</div><div>2+ years building production LLM or AI systems</div><div>Hands-on experience with agentic workflows</div><div>Experience with tool calling, retrieval, and multi-step reasoning</div><div>Strong prompt and context engineering skills</div><div>Experience building evaluation frameworks for AI outputs</div><div>Strong Python and backend fundamentals</div><div>Experience handling hallucinations, edge cases, and cost control</div><div>Based in San Francisco</div><div><br></div><div>Nice to Have</div><div>Experience integrating AI into enterprise SaaS systems</div><div>Experience with vector databases</div><div>Experience designing HITL systems</div><div>Experience with scaling AI workloads</div><div><br></div>