We are hiring an Artificial Intelligence Engineer in Dubai with strong experience in Python and software development, plus hands-on expertise with LiteLLM, including proxy/gateway configuration, multi-model integration, model routing and fallbacks, load balancing, authentication, and rate limiting for production LLM systems.
About the Role – LLM Infrastructure & Generative AI Engineering
Core Focus: LiteLLM Proxy/Gateway, multi-model integration, and LLM API management
LLM Providers: OpenAI/Azure OpenAI, Anthropic, Google Gemini, AWS Bedrock, and open-source LLMs (Llama, Mistral)
RAG & Vector Databases: Pinecone, Weaviate, Milvus, Chroma, FAISS, Elasticsearch/OpenSearch
Frameworks: LangChain, LlamaIndex, Semantic Kernel, and REST APIs via FastAPI/Flask
Deployment: Docker, Kubernetes, CI/CD, and cloud platforms (Azure, AWS, GCP)
Career Growth & Applied AI Impact
Strategic Location: Dubai – a growing hub for applied AI and generative AI infrastructure development
Cutting-Edge Stack: Work hands-on with LiteLLM proxy architecture across multiple LLM providers
Full RAG Pipeline Exposure: From vector database selection to retrieval-augmented generation architecture
Career Growth: Build deep, production-grade expertise in one of the fastest-growing fields in software engineering
Position Overview
This Artificial Intelligence Engineer role requires strong Python and software development experience combined with hands-on LiteLLM expertise across proxy/gateway setup, multi-model integration, model routing and fallbacks, load balancing, authentication, and usage monitoring. You will work with LLM APIs and generative AI concepts across multiple providers, implement RAG architecture with vector databases, build with frameworks like LangChain and LlamaIndex, develop REST APIs, and deploy production systems using Docker, Kubernetes, and cloud platforms.
Why This Role Matters: As Artificial Intelligence Engineer, you build production-grade LLM infrastructure using LiteLLM, managing routing, fallbacks, and load balancing across multiple AI providers, implement RAG pipelines and vector database architecture that power intelligent retrieval systems, work hands-on with the industry’s leading LLM providers including OpenAI, Anthropic, and AWS Bedrock, develop Agentic AI systems and deterministic LLM programming for real production use cases, and build deep expertise deploying containerized AI systems with Docker, Kubernetes, and modern CI/CD pipelines.
Key Responsibilities
LiteLLM Infrastructure & Multi-Model Integration
- Configure and manage LiteLLM Proxy/Gateway for production LLM traffic
- Implement multi-model integration, routing, and fallback strategies
- Manage load balancing, authentication, access control, and rate limiting
- Monitor usage and performance across multiple LLM endpoints
LLM & Generative AI Development
- Apply strong understanding of LLM APIs and generative AI concepts
- Work with LLM providers including OpenAI/Azure OpenAI, Anthropic, Google Gemini, AWS Bedrock, and open-source models
- Build applications using frameworks such as LangChain, LlamaIndex, or Semantic Kernel
RAG Architecture & Vector Databases
- Design and implement RAG (Retrieval-Augmented Generation) architecture
- Work with vector databases including Pinecone, Weaviate, Milvus, Chroma, FAISS, and Elasticsearch/OpenSearch
API Development & Production Deployment
- Develop REST APIs using FastAPI, Flask, or similar frameworks
- Deploy containerized applications using Docker and Kubernetes
- Support CI/CD pipelines and Git-based version control for production deployment
- Work across cloud platforms including Azure, AWS, or GCP
Qualifications & Requirements
Core Technical Requirements
- Strong experience in Python and software development
- Hands-on experience with LiteLLM, including proxy/gateway, multi-model integration, and load balancing
- Strong understanding of LLM APIs and generative AI concepts
LLM & RAG Experience
- Experience with one or more LLM providers (OpenAI, Anthropic, Google Gemini, AWS Bedrock, or open-source LLMs)
- Experience with RAG architecture and vector databases
- Experience with frameworks such as LangChain, LlamaIndex, or Semantic Kernel
Infrastructure & Deployment Skills
- Experience developing REST APIs using FastAPI, Flask, or similar frameworks
- Good understanding of Docker and containerized deployments
- Experience with cloud platforms (Azure, AWS, or GCP)
- Familiarity with CI/CD, Git, Kubernetes, and production deployment practices
Experience Requirements
- 1+ years of work experience with Deterministic LLM Programming
- 1+ years of work experience with Agentic AI Development
- 1+ years of work experience with Python programming
About This AI Engineering Opportunity
This role sits within an AI engineering team in Dubai building production-grade LLM infrastructure, RAG pipelines, and Agentic AI systems. The position requires deep hands-on skill with LiteLLM, vector databases, and modern deployment practices, offering strong career growth for engineers who want to specialize at the leading edge of applied generative AI infrastructure.
Career Excellence: Build production-grade LLM infrastructure and RAG systems at the forefront of applied AI engineering in Dubai.
Who Should Apply?
- LiteLLM/LLM Infrastructure Engineers: With hands-on proxy/gateway and multi-model routing experience
- RAG/Vector Database Specialists: Skilled with Pinecone, Weaviate, FAISS, or similar tools
- LangChain/LlamaIndex Developers: Comfortable building generative AI applications
- Python Backend Engineers: With FastAPI/Flask and containerized deployment experience
- Agentic AI Developers: Interested in deterministic LLM programming and production AI systems
Recently opened JOBS 👇🏻
C++ Developer Jobs Dubai UAE 2026
Junior Web Developer Jobs Sharjah UAE 2026
