4 days ago
Base Salary
$130k - $220k/yr
Responsibilities
- Build response-generation pipelines for request classification, context assembly, tool selection, response generation, and escalation.
- Develop retrieval systems that ground responses in current customer information.
- Create orchestration layers for multi-step workflows and robust third-party API failure handling.
- Build evaluation frameworks using real conversations to measure quality and identify regressions.
- Implement observability and tracing for system behavior analysis.
- Develop controls and interfaces that allow non-technical teams to adjust agent behavior.
- Extend capabilities to voice conversations, including real-time transcription and tool use.
- Improve speed and cost through model selection, caching, and prompt optimization while contributing to infrastructure, data pipelines, integrations, and APIs.
Requirements
- At least 3 years of experience building and shipping production systems used by real users.
- Production experience with AI or machine learning systems, including retrieval pipelines, prompt engineering, or model orchestration.
- Experience building and evaluating retrieval systems such as knowledge bases, ranking, context validation, or semantic search.
- Experience designing multi-step workflows, tool orchestration, or function-calling systems and integrating third-party APIs with production failure handling.
- Proficiency in a backend language such as Python, Go, Rust, or Java, with experience across multiple areas of the stack.
- Experience with evaluation methods and observability or debugging for complex systems.
- Experience with real-time applications, voice systems, user-facing controls, or cost and latency optimization is relevant.
Benefits
- Base salary of $130,000 to $220,000 annually, plus equity of 0.20% to 1.20%.
- Health insurance and a 401(k) match.
- On-site work in San Francisco, California.
- Visa sponsorship is not available.