AI Inference QA & Reliability Engineer

About This Role

About Dizzaract

Dizzaract is a UAE-based game development studio founded in 2022, headquartered at Yas Creative Hub, Abu Dhabi. We develop cutting-edge AI-powered games and systems, including our innovation R&D laboratory FAR labs, the upcoming hero shooter Farcana, and the AI gaming identity platform GAMED. Our research and development team boasts over 100 peer-reviewed papers and more than 20 patents in AI-driven gameplay, digital ownership, and competitive design. With a diverse team of more than 80 professionals from over 20 countries, we are committed to innovation, excellence, and building a culture that drives performance and results.

The Mission: To capture enterprise traffic from the likes of OpenAI and Anthropic, our network must be mathematically flawless and virtually indestructible. You are the adversary. Your job is to break the network, find latency spikes, expose memory leaks, and mathematically verify that our optimized tensor operations produce accurate outputs.

What You Will Do:

• Adversarial Load Generation: Build custom, high-concurrency stress testing frameworks (bypassing standard HTTP bottlenecks) to flood the network and simulate massive, coordinated traffic spikes.
• Mathematical Verification: Develop automated test suites to compare our engine's output logits against baseline models to ensure our low-level kernel optimizations and quantizations do not degrade model intelligence.
• Chaos Engineering: Introduce automated network partitions, node failures, and hardware degradation into the production-like environment to prove the network's zero-intervention self-healing capabilities.
• SLA & Benchmarking: Continuously benchmark our Time To First Token (TTFT), Tokens Per Second (TPS), and latency against OpenAI, Claude, and OpenRouter APIs. If we fall behind, you flag the regression.
• Automated Release Gates: Build rigorous, fully automated CI/CD pipelines where performance regressions or packaging errors strictly block deployments.

What We Are Looking For:

• Strong programming skills (Python, Rust) to build custom load-generation and testing tools from scratch.
• Deep understanding of LLM evaluation metrics, perplexity, and how to use "LLM-as-a-judge" for automated quality assurance.
• Experience with chaos engineering and distributed systems failure modes.
• A meticulous, destructive mindset: you take pride in finding the edge cases that bring complex infrastructure to its knees.

Work Location: In person