3 months ago
Base Salary
$180k - $230k/yr
Responsibilities
- Build and improve LLM-based conversational agents, including orchestration, conversation flow, tool use, and voice capabilities.
- Develop embeddable, adaptive generative UI widgets and customer-facing tools for configuring agents, managing flows, reviewing conversations, and measuring performance.
- Build evaluation and self-improvement pipelines, automated regression tests, observability tooling, and systems for tracing and preventing quality regressions.
- Design agent versioning, preview-environment, feature-flag, and rollout infrastructure.
- Develop production backend services and infrastructure in Python and interactive frontend experiences in React.
- Deploy and operate production services on AWS or GCP using Docker and potentially Kubernetes or similar orchestration.
- Prototype rapidly, debug customer issues, document design decisions, and participate in on-call or incident-response rotations.
Requirements
- Proven experience designing and building LLM-based conversational agents with orchestration, tool use, prompt engineering, and conversation flow.
- Production backend development experience in Python, including services, APIs, and backend infrastructure.
- Frontend experience with React and interactive, adaptive UI development.
- Demonstrated ability to deliver full-stack features across frontend, backend, integration, and deployment.
- Experience building evaluation pipelines, automated regression tests, observability tooling, and CI/CD workflows.
- Experience designing deployment and versioning infrastructure for agents, including feature flags, preview environments, and versioned rollouts.
- Experience with voice-enabled or browser-based agents, such as STT/TTS, WebRTC, or browser automation, or equivalent voice/browser and LLM integration experience.
- Experience deploying and operating production services on AWS or GCP with Docker; Kubernetes or similar orchestration is a plus.
- Strong product sense, rapid prototyping ability, and experience prioritizing high-impact work in fast-moving environments.
- Experience at an early-stage startup or demonstrated ability to work effectively in ambiguous, high-velocity environments.
- Strong written and verbal communication skills, including customer debugging and clear technical documentation.
- Willingness to support urgent production issues and participate in on-call or incident-response rotations.
- Familiarity with reinforcement learning workflows, including RL, RLHF, reward modeling, or experimentation frameworks applied to agent improvement is preferred.
Benefits
- Salary of $180,000–$230,000 USD annually.
- Early-stage equity commensurate with the founding engineer role.
- Visa sponsorship is not available; candidates must be legally authorized to work in the United States.
- Fully on-site in San Francisco, California, five days per week; remote and hybrid arrangements are not available.