← All jobs

Applied AI Engineer (Full-Stack)

Pinecone · New York City

Overview

Build end-to-end AI applications, reference architectures, and developer tools showcasing vector search and retrieval infrastructure for the applied AI team at Pinecone.

Skills

PythonTypeScriptReactVector DatabaseRAGLLMAPIsCloud Infrastructure

Responsibilities

  • Design and ship end-to-end AI applications using retrieval and knowledge infrastructure
  • Develop full-stack solutions spanning frontend, backend, APIs, and LLM integrations
  • Build reference applications and reusable components for developer adoption
  • Experiment with RAG, agents, tool use, and context engineering
  • Evaluate and improve AI application quality, latency, and cost

Requirements

  • Strong software engineering background building production applications
  • Proficiency in Python and/or TypeScript with modern backend and frontend tech
  • Experience building APIs and working with databases and cloud infrastructure
  • Hands-on experience building applications using LLMs, embeddings, and vector databases

About Pinecone

Pinecone builds vector database and AI knowledge platforms for developers and enterprises.

What to prepare

RAG architectureAgentic systemsFull-stack system designRetrieval evaluation
Summarised by AI from the job post. Check the full post before applying.
Full job post · as written by Pinecone

ABOUT PINECONE

Pinecone is the trusted AI knowledge company. Its trusted AI knowledge platform—including its Database, Nexus, and Marketplace products—power accurate, fast, and cost-effective AI applications for more than 10,000 customers and 1M developers worldwide. Pinecone's mission is to make AI knowledgeable.

ABOUT THE TEAM AND ROLE

We're looking for an Applied AI Engineer who loves building real applications with AI. You'll work across the stack, from backend services and retrieval pipelines to APIs and user-facing applications, turning new AI capabilities into working solutions.

This is a hands-on engineering role for someone who enjoys moving quickly, experimenting with emerging technologies, and owning projects from initial idea to production.

You'll work closely with our engineering and product teams, as well as customers and partners, to explore new use cases, build reference applications, and demonstrate what's possible with Pinecone's technology.

The ideal candidate combines strong full-stack engineering skills with practical experience building LLM-powered applications and agentic systems. You should be equally comfortable discussing architecture, writing production code, and putting together a working prototype.

RESPONSIBILITIES

  • Design, build, and ship end-to-end AI applications using Pinecone’s retrieval and knowledge infrastructure.
  • Develop full-stack solutions spanning frontend interfaces, backend services, APIs, data pipelines, and LLM integration.
  • Build reference applications, integrations, and reusable components that help developers and customers adopt Pinecone.
  • Experiment with emerging AI patterns, including RAG, agents, tool use, context engineering, and agent memory.
  • Work with customers, partners, and internal teams to understand real-world problems and translate them into working software.
  • Evaluate and improve the quality, reliability, latency, and cost of AI-powered applications.
  • Share technical insights and best practices through code, examples, and technical content.
  • Bring learnings from building applications back into Pinecone’s product and engineering teams.

WHAT YOU’LL BRING TO THE TABLE

You don't need to check every box, but you should enjoy building software and be excited about what AI makes possible.

FULL-STACK ENGINEERING

  • Strong software engineering background with experience designing, building, and shipping production applications.
  • Proficiency in Python and/or TypeScript, including modern backend frameworks and frontend technologies such as React or Next.js.
  • Experience building APIs, integrating external services, and working with databases and cloud infrastructure.
  • Ability to independently take a project from rough requirements through implementation and deployment.

APPLIED AI

  • Hands-on experience building applications using LLMs, embeddings, vector databases, or retrieval-augmented generation.
  • Familiarity with modern AI development tools, frameworks, and APIs.
  • Understanding of the practical challenges of building AI applications, including retrieval quality, evaluation, latency, reliability, and cost.
  • Curiosity about emerging patterns in agentic applications, context management, and AI-driven workflows.

OWNERSHIP & COLLABORATION

  • A builder's mindset: you enjoy writing code, experimenting, and getting working software into users’ hands.
  • Comfortable working with ambiguous requirements and making…