9 hours ago
Base Salary
$130k - $220k/yr
Responsibilities
- 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.
- Create reliable multi-step tool workflows and handle third-party API failures.
- Build evaluation frameworks using real conversations to measure quality and catch regressions.
- Implement observability and tracing for understanding system behavior.
- Develop interfaces that let non-technical users adjust agent behavior.
- Extend agent capabilities to voice through real-time transcription and tool use.
- Improve speed 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.
- Substantive startup or founder experience shipping real products.
- Experience designing and debugging production AI systems, especially retrieval pipelines, prompt engineering, and model orchestration.
- Strong retrieval experience, such as knowledge bases, ranking, context validation, or semantic search, along with methods for evaluating production systems.
- Experience with multi-step workflows, tool orchestration or function calling, and observability or debugging for complex pipelines.
- Proficiency in a backend language such as Python, Go, Rust, or Java, with the ability to work across multiple stack layers.
- Experience integrating third-party APIs and managing production failure modes.
- Experience with real-time systems, voice, user-facing controls, or model cost and latency optimization is valuable.
Benefits
- Health insurance.
- 401(k) match.
- On-site work in San Francisco, California.
- Base salary of $130,000 to $220,000 annually plus equity of 0.20% to 1.20%.