Staff AI Engineer – Lead AI-First Full-Stack Systems

People In AI; San Francisco (CA); On-site; USD 250,000 - 310,000; Full time

Job summary

People In AI in San Francisco is seeking a Staff AI Engineer to lead building infrastructure and user-facing systems powering AI-first features. You will ship production-ready AI components, scale internal platforms, and set technical direction across backend and frontend.

You'll work with TypeScript, React, Node.js, and AWS, integrate LLMs, design RAG pipelines, and mentor engineers while collaborating with product, design, and ML teams to transform legacy workflows into intelligent systems.

Qualifications

• Experience with TypeScript, React, Node.js, and AWS.
• Experience integrating LLMs or building AI-powered features.
• Familiarity with RAG, vector databases, and prompt engineering.
• Track record of taking complex systems to production.
• CI/CD, observability, and cloud-native infrastructure.

Responsibilities

• Build full-stack systems that integrate applied LLM features into core product experiences.
• Design and scale backend services for RAG pipelines, vector search, and AI orchestration.
• Develop intuitive frontend interfaces for AI copilots using modern React patterns.
• Lead architecture and implementation of AI-powered workflows across teams.
• Strengthen internal tooling for prompt iteration, evaluation, and observability.
• Collaborate closely with product, design, and ML teams to bring features to life.
• Mentor engineers and influence engineering best practices across the org.

Skills

TypeScript

React

Node.js

AWS

LLMs

AI-powered features

Tools

Open-source LLM frameworks

Orchestration tooling

Job description

People In AI in San Francisco is seeking a Staff AI Engineer to lead building infrastructure and user-facing systems powering AI-first features. You will ship production-ready AI components, scale internal platforms, and set technical direction across backend and frontend.

You'll work with TypeScript, React, Node.js, and AWS, integrate LLMs, design RAG pipelines, and mentor engineers while collaborating with product, design, and ML teams to transform legacy workflows into intelligent systems.