AI Inference Data Engineer

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: An inference network routing millions of requests globally generates a massive, complex data exhaust. You will build the data plane that fuels our routing intelligence, telemetry, and distributed memory systems. To beat OpenRouter, our network needs to route requests intelligently based on real-time hardware metrics and cost analysis without adding latency.

What You Will Do:

• High-Throughput Telemetry: Design pipelines to ingest, process, and analyze millions of telemetry events per second (GPU utilization, TTFT, inter-token latency) from distributed nodes.
• Distributed KV-Cache Architecture: Architect the data layer for distributed KV-cache storage and retrieval, allowing the network to context-switch efficiently across different compute nodes.
• Intelligent Routing State: Build the real-time data stores that power our routing layer, ensuring the network always knows the exact state, cost, and availability of every node globally.
• Ledger & Analytics: Develop the backend pipelines for billing, rate-limiting, and auditing, ensuring airtight data consistency for high-frequency micro-transactions.
• Data Packaging: Ensure all data infrastructure deployments are containerized, immutable, and require zero manual configuration upon deployment.

What We Are Looking For:

• Expertise in high-throughput messaging and streaming systems (e.g., Redpanda, Kafka) and real-time OLAP databases (e.g., ClickHouse).
• Strong proficiency in backend languages (Rust, Go, or Python) with a focus on high concurrency and low latency.
• Experience with vector databases and managing massive, distributed state.
• A strong grasp of distributed consensus algorithms and data replication across decentralized environments.

Work Location: In person