Applied AI Engineer at Enum Technology & Solution Pvt Ltd

Enum Technology & Solution Pvt Ltd; Dubai; On-site; AED 81,000 - 97,000; Full time

Job summary

Enum Technology & Solution Pvt Ltd is seeking an Applied AI Engineer to design, build, and deploy production‑grade AI systems at government scale. You will work on LLM-driven applications, RAG systems, AI agents, and robust evaluation frameworks in real environments.

Expect hands-on Python development, strong software fundamentals, and a focus on reliability, observability, and performance across platform integrations.

Qualifications

• 5+ years of experience in Applied AI Engineering or related roles.
• Experience building and deploying production AI/ML systems.
• Strong proficiency in Python.
• Solid software engineering fundamentals including design, testing, and performance.
• Deep understanding of LLMs, their behavior and limitations.
• Experience designing AI evaluation frameworks.
• Knowledge of offline and online evaluation and regression detection.
• Strong architecture, scalability, reliability and observability.
• Excellent written and verbal communication skills.

Responsibilities

• Design and deploy production AI applications powered by large language models.
• Build end-to-end RAG systems with ingestion, embeddings and retrieval.
• Develop AI agent systems supporting multi-step reasoning and tool use.
• Design and implement AI evaluation frameworks with metrics and regression checks.
• Address LLM limitations like hallucination, latency and prompt sensitivity.
• Develop reliable and scalable APIs for AI services.
• Integrate AI capabilities with existing platforms and data sources.
• Translate operational requirements into engineering problems with measurable outcomes.
• Build reusable AI infrastructure and patterns for government-scale use.

Skills

Python

LLMs

RAG systems

AI agents

Evaluation frameworks

Production API design

Observability

System design

Documentation

Software engineering

Education

MSc in CS/AI

PhD in CS/AI

Tools

LangGraph

LangChain

AutoGen

Semantic Kernel

CrewAI

vLLM

TensorRT-LLM

Job description

This Full time on site position offers great opportunities for career growth.

We are looking for an Applied AI Engineer to design, build, and deploy production‑grade AI systems at government scale. The ideal candidate will have strong hands‑on experience with LLMs, RAG, AI agents, evaluation frameworks, and production AI infrastructure, along with solid Python and software engineering fundamentals. This role is focused on applying AI in real‑world production environments rather than research prototypes alone.

Key Responsibilities

• Design and deploy production AI applications powered by large language models.


• Build end-to-end RAG systems, including document ingestion, embeddings, vector databases, semantic retrieval, reranking, and grounding evaluation.


• Develop AI agent systems supporting multi-step reasoning, planning, and tool use.


• Design and implement AI evaluation frameworks, including offline and online metrics, quality measurement and regression detection.


• Identify and address LLM limitations such as hallucination, context degradation, prompt sensitivity, latency, and output reliability.


• Develop reliable and scalable APIs for AI services.


• Integrate AI capabilities with existing platforms, applications, and data sources.


• Translate operational requirements into clearly defined engineering problems and measurable outcomes.


• Build reusable AI infrastructure and engineering patterns that can scale across multiple government entities.


• Ensure systems meet requirements for scalability, reliability, performance, and observability.

Required Qualifications

• 5+ years of experience in Applied AI Engineering, AI/ML engineering, or a combination of research and engineering.


• Demonstrated experience building and deploying production AI/ML systems.


• Strong proficiency in Python.


• Strong software engineering fundamentals, including system design, testing, debugging, and performance optimization.


• Deep understanding of Large Language Models (LLMs) and their behaviour and limitations.


• Experience designing or implementing AI evaluation frameworks.


• Understanding of offline evaluation, online monitoring, and regression detection.


• Strong knowledge of architecture, scalability, reliability, and observability.


• Strong written and verbal communication skills.

Preferred Qualifications

• MSc, PhD, or research experience in Computer Science, AI, ML, NLP, or a related field.


• Hands‑on experience building RAG systems end‑to‑end.


• Experience with LangGraph, LangChain, AutoGen, Semantic Kernel, CrewAI, or similar frameworks.


• Knowledge of LLM inference behaviour, decoding strategies, prompt sensitivity, and latency optimization.


• Experience with vLLM, TGI, TensorRT-LLM, or equivalent GPU‑based inference technologies.


• Experience with voice and conversational AI, including STT/TTS or real‑time conversational systems.


• Publications, preprints, or research contributions in NLP, ML systems, retrieval, or related areas.

Pay: From AED8,000.00 per month

Work Location: In person