AI Engineer Intern

Title: AI Engineer Intern
Location: Remote
Department: Engineering
Engagement Type: Full-Time
Duration: 6-Month Paid Contract

About the Company

Niflor designs AI-native enterprise systems where intelligence must operate reliably under production constraints.

We focus on applied AI , integrating intelligent systems into structured workflows with measurable outcomes.

Role Overview

We are hiring an AI Engineer Intern to work on LLM integration, agentic frameworks, and production AI orchestration systems.

This role involves building applied AI systems, not just experimenting with APIs.

Core Technology Stack

LLM Integration: OpenAI / open-weight models
Agentic Frameworks: LangGraph, CrewAI, AutoGen (or similar)
Architecture: RAG systems
Data: Embeddings, vector databases
Backend Integration: Python

Responsibilities

• Design and implement LLM-based workflows
• Work with agentic frameworks for multi-step reasoning systems
• Build Retrieval-Augmented Generation (RAG) systems
• Integrate LLM capabilities into backend services
• Evaluate model outputs and detect hallucination risks
• Optimize prompts and system performance
• Build evaluation pipelines for AI reliability

Required Qualifications

• Strong understanding of ML fundamentals
• Understanding of transformer architecture basics
• Experience working with LLM APIs
• Knowledge of embeddings and vector databases
• Strong Python proficiency
• Ability to evaluate and debug model behavior

Preferred Qualifications

• Experience with agentic frameworks
• Experience with RAG pipelines
• Experience fine-tuning models
• Backend systems integration experience

What We Value

• System-level AI thinking
• Analytical mindset
• Measured experimentation
• Production reliability focus
• Independent execution

Compensation & Contract

• Fully paid internship
• 6-month contract
• Fully remote
• Potential transition to Applied AI engineering role