AI Data Engineer (Gen AI)

Job Description

We are seeking a part-time AI/Data Engineer to join our engineering team and support client-facing AI initiatives.

This role is focused on connecting structured and unstructured data sources to Large Language Models (LLMs), engineering and evaluating prompts for accuracy and usefulness, and delivering lightweight application outputs.

The position is initially ~15 - 20 hours per week, with potential to scale as client demand grows.

• To Note: This is for an immediate project need. Candidates should be readily available to be onboarded.
  
  

Responsibilities:

• Integrate client data sources (documents, CMS/CRM content, spreadsheets, APIs) into secure pipelines accessible by LLMs.
• Engineer and refine prompts to improve quality, accuracy, and consistency of LLM outputs.
• Establish evaluation methods for measuring prompt effectiveness and model responses.
• Work alongside existing AI engineers to implement core AI functionality.
• Deliver lightweight frontend outputs (e.g., query box + results display) when required; leverage frameworks or prebuilt patterns where possible.
• Follow internal guidelines for security and data handling, especially when working with proprietary or client data.
• Collaborate closely with the internal engineering team for support and technical alignment.
  
  

Requirements:

• 3+ years of professional experience in AI/ML engineering, data engineering, or backend software development.
• Strong proficiency with Python and experience integrating APIs, databases, or file-based data.
• Hands-on experience with LLMs and frameworks such as LangChain, LlamaIndex, or similar.
• Demonstrated skill in prompt engineering and evaluating model outputs.
• Familiarity with vector databases (e.g., Pinecone, Chroma, pgvector).
• Basic frontend development skills (React/Next.js or similar) to deliver simple UIs for results.
• Strong communication skills and ability to work remotely in a distributed team.
  
  

Nice to Have:

• Experience with regulated or proprietary datasets and compliance-aware architectures.
• Exposure to enterprise security practices (auth, encryption, audit logging).
• Previous consulting or client-facing project experience.