Sr Backend AI Engineer

Senior AI Engineer — Agentic AI Startup

Role Overview

Our client is a well-funded, AI startup building a multi-agent platform that transforms how professionals interact with complex, high-value technical products in stealth environments.

The organization is looking for a Senior AI Engineer to own the entire backend and AI stack, from architecture through deployment and continuous improvement. You will report directly to the CEO and operate with full technical autonomy. This is not a "ticket-taker" role; you will design the system, choose the tools, ship the product, and play an instrumental role in growing the engineering team.

This is a rare opportunity to join at the earliest stage, shape the technical roadmap of an agentic AI product with real users and real revenue, and build the engineering foundation of a company with significant upside.

Responsibilities

You have end-to-end ownership of the backend and AI systems for a product that demands exacting precision. You'll work closely with a small, accomplished, low-ego team and have direct exposure to customers whose work has meaningful real-world impact.

• Own the full backend architecture: design, build, deploy, monitor, and iterate — with autonomy over tech stack decisions
• Build and improve production RAG pipelines including ingestion, retrieval, reranking, and citation/source-attribution across multi-modal data (text, images, diagrams, PDFs)
• Drive AI quality through rigorous evaluation, prompt engineering experimentation, and grounding — treating accuracy as a product requirement, not an afterthought
• Ship agentic AI features that deliver domain-expert-level guidance to non-technical and technical users.

Required Qualifications

• 4+ years building and deploying backend services in a production environment.
• 1–2 years building LLM-powered products in production environments, including hands-on work with foundation model APIs (Such as OpenAI or Anthropic APIs)
• Built or contributed meaningfully to RAG pipelines (vector databases, embedding models, chunking strategies, search and reranking, etc)
• Experience deploying to major cloud platforms (AWS, GCP, or Azure)
• Currently using AI coding tools (Claude Code, Cursor, Copilot, or similar) as part of your daily workflow

Preferred Qualifications

• Experience building AI products in high-stakes domains where accuracy is critical (i.e. healthcare, compliance, finance, field services, or similar regulated environments)
• Exposure to multi-modal RAG pipelines.
• Prior startup experience or a demonstrated track record of building from scratch inside a larger organization
• Experience mentoring or leading other engineers

Location

San Francisco Bay Area preferred, but Remote within the contiguous US is OK.