AI Engineer | Python, LLMs, RAG & AI Agents (On-site)

Quantin; Dubai; On-site; AED 320,000 - 520,000; Full time

Job summary

Quantin.ai is an early-stage AI startup in Dubai. We’re seeking an AI Engineer with strong Python skills to build backend services, RAG pipelines, and integrate LLMs and AI agents with databases and tools. You’ll optimize performance and reliability while collaborating on product development and testing.

On-site in Dubai, with opportunities to shape growing platform. Experience with Python, FastAPI, LLMs, vector search, and tools like LangChain, PyTorch, and Docker will help you excel.

Qualifications

• Proficient in Python with API development experience.
• Hands-on with LLMs, embeddings, vector search and RAG architectures.
• Experience with LangChain or LlamaIndex.
• Familiar with Hugging Face and Transformers.
• Experience with PostgreSQL and Redis.
• Familiar with vector search tools: Qdrant, pgvector or FAISS.
• Comfortable using Git, Docker and Linux.
• Nice to have PyTorch and deploying models with vLLM or llama.cpp.

Responsibilities

• Develop backend services and APIs using Python and FastAPI.
• Build RAG pipelines for document retrieval and grounded responses.
• Connect LLMs and AI agents to databases, tools and services.
• Evaluate and improve response quality, inference speed and reliability.
• Collaborate with the team on product development, testing and decisions.

Skills

Python

LLMs

Embeddings

RAG architectures

LangChain

LlamaIndex

Hugging Face

Transformers

PostgreSQL

Redis

Qdrant

pgvector

FAISS

Git

Docker

Linux

PyTorch

vLLM

llama.cpp

Tools

Python

FastAPI

Job description

At Quantin.ai, we are an early-stage AI startup developing intelligent products built around language models, AI agents and connected data.

We’re expanding our technical team and looking for an AI Engineer with strong Python skills who enjoys solving practical problems, experimenting with new approaches and turning ideas into working products.

What you’ll work on

• Develop backend services and APIs using Python and FastAPI
• Build RAG pipelines for document retrieval and grounded response generation
• Connect LLMs and AI agents to databases, tools and application services
• Evaluate and improve response quality, inference speed and system reliability
• Collaborate with the team on product development, testing and technical decisions

What we’re looking for

• Strong proficiency in Python and hands-on experience developing software and APIs
• Practical understanding of LLMs, embeddings, vector search and RAG architectures
• Experience with LangChain or LlamaIndex
• Familiarity with Hugging Face and Transformers
• Experience working with PostgreSQL and Redis
• Familiarity with vector search tools such as Qdrant, pgvector or FAISS
• Confidence using Git, Docker and Linux

Experience with PyTorch, deploying open-source models using vLLM or llama.cpp, and optimizing inference performance and GPU memory usage would be a plus.

We value clear communication, curiosity and the ability to take ownership of your work in a growing startup.

Location and interviews

Dubai, United Arab Emirates — on-site

This position requires working in person with our team in Dubai.

Interviews can be conducted online or in person, by prior arrangement.