Full-Stack AI Engineer for LLM Apps & RAG

Pinecone; United States; Hybrid; USD 120,000 - 180,000; Full time

Benefits offered by this job

Health coverage

401(k) plan

Equity award

Flexible time off

Paid parental leave

Annual company retreat

WFH equipment stipend

Job summary

Pinecone is seeking an Applied AI Engineer to build real AI-powered applications across the stack, from backend services and retrieval pipelines to APIs and user interfaces. You will own projects from idea to production, collaborating with engineering, product, customers, and partners to explore new use cases and demonstrate Pinecone’s technology.

The role combines strong software engineering with practical experience in LLM-powered systems, agentic workflows, and production-quality prototypes,

Qualifications

• Experience building production-ready AI applications.
• Strong full-stack engineering skills with LLM experience.
• Ability to design and implement retrieval pipelines and APIs.

Responsibilities

• Design, build, and ship end-to-end AI applications using retrieval and knowledge infrastructure.
• Develop full-stack solutions spanning frontend interfaces, backend services, APIs, data pipelines, and LLM integration.
• Experiment with patterns like RAG, agents, tool use, and context engineering.
• Work with customers, partners, and internal teams to translate problems into software.
• Evaluate and improve quality, latency, and cost of AI-powered apps.

Skills

Python

TypeScript

LLM-powered apps

Full-stack development

APIs

Retrieval pipelines

Agentic systems

Tools

React

Next.js

Vector databases

Cloud infra

Job description

Pinecone is seeking an Applied AI Engineer to build real AI-powered applications across the stack, from backend services and retrieval pipelines to APIs and user interfaces. You will own projects from idea to production, collaborating with engineering, product, customers, and partners to explore new use cases and demonstrate Pinecone’s technology.

The role combines strong software engineering with practical experience in LLM-powered systems, agentic workflows, and production-quality prototypes,