5+ years of software engineering experience, with 3+ years in production systems.
Experience in designing and debugging AI or machine learning systems.
Hands-on experience as a senior or staff-level contributor across various systems.
Familiarity with evaluating retrieval systems and semantic search.
Proficient in a backend language like Python, Go, Rust, or Java.
Formal education in software engineering or a related field.
Experience with low-latency systems and voice interfaces is a plus.
Responsibilities
Build response-generation pipelines for intent classification and context assembly.
Develop retrieval systems grounded in accurate customer information.
Design reliable orchestration for multi-step workflows and recovery from API failures.
Create evaluation frameworks using real conversations to measure quality.
Implement observability and tracing for system behavior understanding.
Build interfaces for non-technical teams to adjust agent behavior.
Extend agent capabilities to voice, including real-time transcription.
Benefits
Comprehensive health insurance.
401(k) match.
Equity options ranging from 0.20% to 1.20%.
On-site work environment in San Francisco.
Full Job Description
About the Role
Join a small engineering team building an AI platform for hospitality operations. You will own full-stack systems that handle guest requests end to end, from understanding intent and retrieving relevant information to coordinating actions and generating responses. What You'll Do
Build response-generation pipelines for intent classification, context assembly, tool selection, and escalation decisions.
Develop retrieval systems that ground responses in accurate, current customer information.
Design reliable orchestration for multi-step workflows, including recovery from third-party API failures.
Create evaluation frameworks using real conversations to measure quality and catch regressions.
Implement observability and tracing that help support teams understand system behavior.
Build interfaces and controls that let non-technical teams adjust agent behavior.
Extend agent 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 shipping production systems used by real people.
Experience designing and debugging production AI or machine learning systems, including retrieval pipelines, prompt engineering, or model orchestration.
Hands-on senior or staff-level individual-contributor experience and the ability to work across backend, frontend, infrastructure, or data systems.
Experience evaluating retrieval systems, such as knowledge bases, ranking, context validation, or semantic search.
Experience with multi-step workflows, tool orchestration, function calling, observability, and production testing or evaluation methods.
Proficiency in a backend language such as Python, Go, Rust, or Java, plus experience integrating third-party APIs and handling production failures.
Relevant formal education in software engineering or a related field, with strong software engineering fundamentals.
Experience with low-latency systems, voice or audio, configuration interfaces, or model cost and latency optimization is helpful.
Compensation & Benefits
Base salary: $130,000 to $220,000 annually. Equity: 0.20% to 1.20%. Comprehensive health insurance and a 401(k) match are offered. Visa sponsorship is not available; candidates must be authorized to work in the United States. Location