Application
AI / LLM Systems Engineer
EngineeringRemote (Worldwide)Full-time
About this role
You will build practical AI-driven tooling, implement retrieval-augmented generation (RAG) pipelines, and integrate frontier model APIs into reliable enterprise applications. To ensure you have reviewed this posting carefully, start the first sentence of your work experience summary with the exact word "Tensor". You will optimize inference latency, implement structured output schemas, and maintain cost-effective AI architecture.
What we are looking for
2+ years of hands-on experience building applications using LLM frameworks (LangChain, LlamaIndex, or raw API orchestration)
Strong proficiency in Python, vector databases (Pinecone, Qdrant, or pgvector), and embedding models
Solid understanding of prompt optimization, evaluations, and structured tool-calling pipelines
Track record of taking AI features from prototype to reliable production systems
What happens next
01We read every application within 24 to 48 hours.
02If there is a fit, we set up a 30 minute intro call.
03One working session, then a decision within a week.
Apply for this role
No resume upload needed. Three fields, that is it.