13 hours ago
Base Salary
$130k - $220k/yr
Responsibilities
- Design and build systems for classifying guest requests, assembling context, selecting tools, and deciding when to respond or escalate.
- Develop retrieval pipelines that ground responses in accurate and current customer information.
- Build reliable multi-step workflow orchestration and handle third-party API failures during conversations.
- Create evaluation frameworks to assess response quality and prevent regressions before release.
- Implement observability and tracing for system behavior analysis.
- Build no-code controls for non-technical teams to adjust agent behavior.
- Extend agent capabilities to voice conversations with real-time transcription and tool use.
- Improve performance and cost through model routing, caching, and prompt refinement.
- Contribute to infrastructure, data pipelines, integrations, and APIs.
Requirements
- At least 5 years of professional software engineering experience, including 3 or more years building production systems used by real people.
- Experience designing and debugging production AI or ML systems, including retrieval pipelines, prompt engineering, or model orchestration.
- Proficiency across multiple areas such as backend, frontend, infrastructure, or data pipelines.
- Experience building and evaluating retrieval systems, multi-step workflows, and production observability or evaluation tools.
- Proficiency in a backend language such as Python, Go, Rust, Java, or a similar language, plus experience integrating third-party APIs.
- Strong judgment in selecting AI models and measuring quality, reliability, latency, and cost.
Benefits
- Base salary of $130,000 to $220,000 annually plus 0.20% to 1.20% equity.
- Health insurance and a 401(k) match.
- On-site work in San Francisco, California.
- Visa sponsorship is not available.