Coderio Software Company
Senior Agentic AI Developer
Publicada há 1 mês
Candidatar no LinkedInSobre a vaga
<span><strong>Why join us?<br></strong><strong>Handoff is the AI agent that runs a construction company.</strong><span></span>We help remodelers automate estimating, streamline operations, and win more work - backed by real-time cost data, intuitive design, and workflows that “speak contractor.” With over 10,000 monthly active users and $6B in annualized project volume already flowing through our platform, we’re becoming the trusted partner for the people who build our homes.<br><br>We are backed by $25M+ raised from Y Combinator, Initialized, and Greycroft. Our team is distributed across hubs in Austin, São Paulo, and Buenos Aires, and we are deeply focused on building intuitive, high-impact solutions that make a real difference for our users.<br><br><strong>AI Engineer at Handoff<br></strong>You’ll own how well Handoff’s AI works in production: its quality, speed and cost, across all of our products. When something degrades, you find out why, fix it and explain what happened.<br><br>Most of the work is experimentation. You’ll form a hypothesis, test it against evals and real traffic, and ship what the data supports.<br><br><strong>What You'll Do<br></strong><ul><li>Own our core AI metrics and the dashboards and alerts behind them. </li><li>Run experiments on prompts, tools, context and models, from offline evals to controlled rollouts, and decide with data. </li><li>Build the evals and observability that let the whole team ship AI changes safely. </li><li>Improve what customers judge us on: accurate outputs, reliable actions and fast answers. </li><li>Shape the architecture of our agents as the product grows: how context, tools and memory scale. </li><li>Evaluate new models and providers as they are released, and lead migrations when they are worth it. </li><li>Work across Handoff’s products and teams, wherever AI quality, speed or cost needs attention. </li><li>Turn customer-reported AI problems into diagnosed causes and measurable fixes. </li><li>Share what you learn and raise the bar for AI engineering across the team. <br><br><br></li></ul><strong>About You<br></strong><ul><li>You’ve owned an LLM-powered feature or agent in production and can point to a metric you moved. </li><li>You design experiments carefully and can tell a real improvement from noise. </li><li>5+ years of software engineering experience, with strong Python and working knowledge of TypeScript/Node, SQL and cloud-based architectures. </li><li>Practical experience with agents: tool calling, context management, retrieval and structured outputs, ideally with a framework such as LangGraph. </li><li>Experience building evals and using tracing tools such as LangSmith, Langfuse or similar. </li><li>You’re comfortable with ambiguity and switching between problems, and you set your own agenda from the data. </li><li>You care whether the output is right for the customer, not only whether the model call succeeded. </li><li>Proven experience working in a startup environment is a must. <br><br><br></li></ul><strong>What We Offer<br></strong><ul><li>💸 Competitive salary in USD</li><li>💰 Attractive stock options</li><li>🌴 Unlimited PTO</li><li>🚛 Relocation allowance</li><li>👨💻 Top-notch equipment</li><li>🧳 Team offsites around the world!<br><br><br></li></ul>We’re especially excited about engineers who enjoy turning emerging AI capabilities into useful, dependable experiences for real customers.<br><br><strong>Please note that we will only consider applications submitted in English.</strong><button><span><span><span>…</span><span> more</span></span></span></button></span>