AI Engineer, LLM & Agentic Systems

Aumnitech; Dubai; On-site; AED 240,000 - 420,000; Full time

Job summary

Aumnitech in Dubai seeks an experienced software engineer to design and deploy LLM-powered applications, agents, and copilots for client products. You will build RAG pipelines and vector DB integrations, and optimize cost and latency of LLM APIs in production.

You will collaborate with client and product teams to translate business needs into effective AI features, and monitor deployed systems for drift, costs, and reliability, leveraging AWS/Azure/GCP as needed.

Qualifications

• 3+ years of professional software engineering experience, including 1+ years building LLM-based applications.
• Strong Python and working knowledge of LangChain, LlamaIndex, or a comparable orchestration framework.
• Experience with a vector database (Pinecone, Weaviate, pgvector, or similar).
• Solid understanding of prompt design, RAG architecture, and evaluation methods.
• Comfortable working directly on AWS, Azure, or GCP.

Responsibilities

• Design, build, and deploy LLM-powered applications, agents, and copilots for client products.
• Build retrieval-augmented generation (RAG) pipelines and vector database integrations.
• Integrate large language model APIs into production systems with attention to cost and latency.
• Write evaluation harnesses to measure model quality before and after shipping.
• Work directly with client and product teams to turn business requirements into working AI features.
• Monitor deployed AI systems for drift, cost overruns, and reliability issues.

Skills

Python

LangChain/LlamaIndex

Vector databases

Prompt design

RAG architecture

Cloud platforms (AWS/Azure/GCP)

Tools

Pinecone

Weaviate

pgvector

Job description

Builds and ships production AI features for client products: retrieval-augmented generation pipelines, agents, and copilots that move real workflows.

What you\'ll do

• Design, build, and deploy LLM-powered applications, agents, and copilots for client products
• Build retrieval-augmented generation (RAG) pipelines and vector database integrations
• Integrate large language model APIs into production systems with attention to cost and latency
• Write evaluation harnesses to measure model quality before and after shipping
• Work directly with client and product teams to turn business requirements into working AI features
• Monitor deployed AI systems for drift, cost overruns, and reliability issues

Skills

• 3+ years of professional software engineering experience, including 1+ years building LLM-based applications
• Strong Python and working knowledge of LangChain, LlamaIndex, or a comparable orchestration framework
• Experience with a vector database (Pinecone, Weaviate, pgvector, or similar)
• Solid understanding of prompt design, RAG architecture, and evaluation methods
• Comfortable working directly on AWS, Azure, or GCP