ABOUT THE ROLE Join a small engineering team building AI software for hospitality operations. You will own full-stack components of systems that handle guest requests, from understanding intent and retrieving relevant information to coordinating tools and generating responses. WHAT YOU'LL DO - Build response-generation components, including intent routers, orchestrators, and systems for deciding when to respond or escalate. - Develop retrieval pipelines that ground responses in accurate, current customer information. - Create reliable tool orchestration for multi-step workflows, including recovery from third-party API failures. - Build evaluation frameworks to assess real conversations and identify regressions before release. - Implement observability and tracing that help support teams understand system behavior. - Create interfaces and controls that let non-technical users configure agent behavior. - Extend capabilities to voice, including real-time transcription and tool use. - Improve speed and cost through model routing, caching, and prompt refinement, while contributing to infrastructure, data pipelines, integrations, and APIs.
WHAT WE'RE LOOKING FOR - At least 5 years of professional software engineering experience, including 3 or more years building and shipping production systems used by real people. - Substantive startup or founder experience delivering real products. - Experience designing and debugging production AI or machine learning systems, including retrieval, prompt engineering, or model orchestration. - Experience building and evaluating retrieval systems, such as knowledge bases, ranking, context validation, or semantic search. - Experience with multi-step workflows, tool orchestration, or function calling, as well as production evaluation and testing methods. - Proficiency in a backend language such as Python, Go, Rust, or Java, and ability to work across backend, frontend, infrastructure, or data pipelines. - Experience integrating third-party APIs and handling production failure modes, plus observability or debugging for complex pipelines. - Real-time or low-latency systems experience is useful.
Voice, transcription, user-facing configuration tools, and model cost or latency optimization are also relevant. COMPENSATION & BENEFITS Base salary is $130,000 to $220,000 annually, with 0.20% to 1.20% equity. Comprehensive health insurance and a 401(k) match are provided. Visa sponsorship is not available; candidates must be authorized to work in the United States. LOCATION On-site in San Francisco, California.
Job description provided by Clera.
View the original posting
