Applied AI Engineer (Full-Stack)
Recruiter Fit Breakdown & Candid Summary
This hands-on full-stack engineering role requires building production-grade applications, APIs, and user interfaces integrated with LLMs and vector databases.
The ideal candidate brings strong backend/frontend proficiency in Python and TypeScript, alongside practical experience with RAG and agentic workflows.
It is well-suited for builders who thrive in ambiguous environments, enjoy rapid prototyping, and want to influence product direction through customer collaboration.
Candidates without practical experience building LLM-powered applications or modern full-stack systems should not apply.
Role Responsibilities
- 1Design, build, and ship end-to-end AI applications using Pinecone's retrieval and knowledge infrastructure.
- 2Develop full-stack solutions spanning frontend interfaces, backend services, APIs, data pipelines, and LLM integration.
- 3Build reference applications, integrations, and reusable components that help developers and customers adopt Pinecone.
- 4Experiment with emerging AI patterns, including RAG, agents, tool use, context engineering, and agent memory.
- 5Work with customers, partners, and internal teams to understand real-world problems and translate them into working software.
- 6Evaluate and improve the quality, reliability, latency, and cost of AI-powered applications.
Skills Matrix
Must-Have Skills
Nice-to-Have Skills
Will an ATS filter reject your resume for this role?
Check your keyword match score, missing must-have skills, and formatting flags — before you apply.
No signups. Free check in 3 seconds.
Ready to submit your application?
Apply directly on Pinecone's official job portal.