Skip to content
The Devora
Engineering

AI/ML Engineer

Build LLM-backed features and evaluation pipelines for client AI engagements.

MidFull-timeRemote (U.S.-based preferred)

Responsibilities

  • Design and build RAG pipelines and agent workflows
  • Build and maintain evaluation sets for prompt and model changes
  • Integrate vector databases and retrieval systems
  • Monitor production AI systems for quality and cost

What we’re looking for

  • 2+ years working with LLM APIs in production
  • Strong Python skills
  • Experience with LangChain or a comparable orchestration framework

Nice to have

  • Experience fine-tuning open-source models
  • Background in NLP research

Apply for this role

We respond to every application within a week.

Start a project