AI Quality & Reliability Engineer – SRE for Cloud AI

D4Insight; Abu Dhabi; Hybrid; AED 280,000 - 420,000; Full time

Job summary

D4Insight in Abu Dhabi is looking for an AI Quality & Reliability Engineer to own the production readiness of cloud-based AI solutions. This hybrid role blends automated testing, AI model evaluation, and SRE, focusing on frameworks that validate AI outputs while ensuring Azure/AWS infrastructure is resilient and bank-grade compliant.

Responsibilities include designing CI/CD test suites, testing AI services for hallucinations, accuracy, and latency, and implementing chaos engineering with robust

Qualifications

• 7+ years of relevant experience in QA/SRE for AI or cloud apps.
• Strong Python expertise with automation frameworks (PyTest, Selenium, Robot Framework).
• Hands-on Azure or AWS, including networking, scaling, and serverless reliability.
• Experience with AI evaluation: RAG, ROUGE/BLEU, and LLM benchmarks.
• Proficient in monitoring tools: Grafana/Prometheus, Azure Monitor, AWS CloudWatch.
• Experience with CI/CD, Terraform, Bash, and GitHub Actions.

Responsibilities

• Design and execute automated testing frameworks for AI services.
• Test AI solutions for hallucinations, accuracy, content safety, and latency.
• Build CI/CD-integrated test suites to validate logic and infra state.
• Implement Chaos Engineering and load testing for banking-scale backends.
• Develop automated recovery scripts and define SLIs/SLOs.
• Automate security scans and ensure banking data residency and privacy.

Skills

Python

PyTest

Selenium

Robot Framework

Azure

AWS

CI/CD

Terraform

K6

JMeter

Grafana

Prometheus

RAG evaluation

LangSmith

DeepEval

Tools

Azure Monitor

AWS CloudWatch

GitHub Actions

Terraform

Bash

Job description

D4Insight in Abu Dhabi is looking for an AI Quality & Reliability Engineer to own the production readiness of cloud-based AI solutions. This hybrid role blends automated testing, AI model evaluation, and SRE, focusing on frameworks that validate AI outputs while ensuring Azure/AWS infrastructure is resilient and bank-grade compliant.

Responsibilities include designing CI/CD test suites, testing AI services for hallucinations, accuracy, and latency, and implementing chaos engineering with robust