3 days ago
San Francisco, CA, USAMid Level
Base Salary
$130k - $220k/yr
Responsibilities
- Build response-generation pipelines for intent classification, context assembly, tool selection, response generation, and escalation.
- Develop retrieval systems that ground responses in accurate customer data and handle messy inputs.
- Build reliable multi-step tool workflows and manage third-party API failures during conversations.
- Create evaluation frameworks using real conversations to measure quality and catch regressions.
- Implement observability and tracing for complex agent behavior.
- Build interfaces and controls for configuring agent behavior.
- Extend agent capabilities to voice using real-time transcription and tool use.
- Improve model speed and cost through routing, caching, and prompt refinement while owning related infrastructure, data pipelines, integrations, and APIs.
Requirements
- At least 3 years of experience shipping production software used by real people; 5 or more years is relevant experience.
- Experience designing, debugging, and evaluating production AI or ML systems, including retrieval, prompt engineering, or model orchestration.
- Hands-on individual-contributor experience across backend, frontend, infrastructure, or data pipelines.
- Proficiency in a backend language such as Python, Go, Rust, or Java, plus experience integrating third-party APIs.
- Experience with retrieval quality, multi-step workflows or function calling, production evaluation, and observability or tracing.
- Strong software engineering fundamentals supported by relevant formal education.
- Experience with real-time systems, voice, user-facing configuration tools, or model cost and latency optimization is valuable.
Benefits
- Health insurance and a 401(k) match.
- Base salary plus equity is offered.
- On-site work in San Francisco, California.
- Visa sponsorship is not available; candidates must be authorized to work in the United States.