Founding Full Stack Engineer

About The Role

A well-funded, early-stage B2B SaaS startup in the AI-powered sales automation space is hiring its first Founding Engineer. You'll join the CTO as a core member of a tiny, high-caliber team and help set the technical culture for everyone who comes after. The company builds self-improving conversational agents that run product demos 24/7 — adapting to each buyer, handling technical questions, and getting smarter with every conversation. Growth has tripled month-over-month and demand is accelerating.

What You'll Work On

• The Agent: LLM orchestration, conversation flow, tool use, and voice.
• The Experience: Embeddable, generative UI that adapts in real-time — fast-loading, interactive, and responsive across products and screen sizes.
• The Platform: Customer-facing tooling for configuring agents, managing flows, reviewing conversations, and measuring performance.
• Evals & Self-Improvement: Pipelines that measure agent quality and feed learnings back automatically, so demos get smarter without manual intervention.
• Infrastructure: Zero cold starts, instant agent response, and versioning systems that let customers preview changes before they go live.

Day-to-Day Examples

• Debug conversation logs, trace where an LLM lost the thread during a pricing objection, and ship a fix to the orchestration layer by lunch.
• Prototype a generative UI widget in an afternoon based on a whiteboard sketch and have something demo-able by end of day.
• Trace a quality regression to a prompt change, roll it back, and add an automated test to prevent recurrence.
• Design agent versioning infrastructure from scratch so customers can safely preview updates.

What We're Looking For

• Proven experience designing and building LLM-based conversational agents — orchestration, tool use, prompt engineering, and conversation flow.
• Production backend development experience in Python (services, APIs, backend infrastructure).
• Frontend experience with React — building interactive, adaptive UIs and rapid prototyping.
• Demonstrated ability to deliver full-stack features end-to-end: 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 (feature flags, preview environments, versioned rollouts).
• Experience with voice-enabled or browser-based agents (STT/TTS, WebRTC, or browser automation) or equivalent voice/browser + LLM integration experience.
• Experience deploying and operating production services on cloud platforms (AWS or GCP) with Docker; Kubernetes or similar orchestration a plus.
• Strong product sense: ability to rapidly prototype, iterate on feedback, and prioritize high-impact work in a fast-moving environment.
• Experience at an early-stage startup or demonstrated ability to thrive in ambiguous, high-velocity environments.
• Strong written and verbal communication skills — comfortable debugging issues with customers and documenting design decisions clearly.
• Willingness to be available for urgent production issues and participate in on-call or incident response rotations.

Nice to Have

• Familiarity with reinforcement learning workflows (RL, RLHF, reward modeling) or experimentation frameworks applied to agent improvement.

Compensation & Benefits

• Salary: $180,000 – $230,000 USD annually
• Early-stage equity commensurate with founding engineer role
• Visa sponsorship is not available — candidates must be legally authorized to work in the United States

Location

This role is fully on-site in San Francisco, CA, five days per week. Remote or hybrid arrangements are not available for this position.