Founding AI Engineer | Quintess

A-Players • San Francisco, CA

73d • $150,000 - $225,000

About The Position

We’re supporting a fast-growing AI startup backed by top-tier Silicon Valley investors. Their mission: build agentic AI systems that eliminate tedious admin work for industrial technicians — starting with a voice AI agent that listens, thinks, and takes action in real time. The product integrates directly with enterprise maintenance systems (EAM/ERP), helping technicians fix complex assets faster by automating reporting, fault classification, and part ordering. They’re already live with some of the largest global rail operators in the US and Europe — and expanding rapidly.

Requirements

• 4–10 years in AI / backend engineering, ideally in startups or fast-moving environments.
• Strong in Python, LLM integration, and cloud deployment (AWS/GCP).
• Experience building AI agents or real-time systems (speech-to-text, TTS, or streaming).
• Understanding of retrieval-augmented generation (RAG) and data pipelines.
• Passion for solving real problems — not just training models — and learning from users.

Nice To Haves

• Prior experience with LangChain, LlamaIndex, or voice orchestration frameworks.
• Experience integrating AI into enterprise systems or industrial environments.
• Early-stage / founding engineer experience.

Responsibilities

• Build and adapt real-time AI agents for new customer use cases (often from scratch).
• Design and ship RAG-powered voice flows and conversational features.
• Improve the latency, reliability, and robustness of the real-time AI stack.
• Partner directly with users to understand workflows and iterate fast.
• Turn bespoke builds into reusable platform blueprints for scale.

What This Job Offers