Senior Inference Engineer (AI)

Senior Inference Engineer
Remote - Dubai - Abu Dhabi

A unified platform for high-performance AI inference - one API to deploy and run AI models at scale, across cloud, dedicated capacity and clients' own hardware.

This is the senior technical seat for AI serving. You will own the inference serving stack: prefill/decode disaggregation, continuous batching, KV-cache management, speculative decoding, MoE serving, quantization, and GPU performance engineering with CUDA/Triton. You set the serving and measurement roadmap and stay hands-on.

You: strong production experience with LLM inference systems (vLLM, SGLang, TensorRT-LLM or similar), deep GPU performance knowledge (FP8/FP4, memory bandwidth, FLOPs), MoE serving experience, rigorous benchmarking, and technical leadership. Open-source contributions to inference frameworks are a strong plus. English C1.

Offer: real ownership, a small senior team with low bureaucracy, competitive salary with performance-based incentives, 24 days annual leave + public holidays, health insurance.

Apply here: Показать контакты