Jobgether is recruiting a Senior AI Inference Engineer specialising in quantised vision, audio and compression (QVAC) workloads, in a fully remote setup ideal for Dubai-based talent. This is a deep-tech role for engineers passionate about squeezing performance out of modern AI systems.
About the Role
You will own the inference stack for multi-modal AI models — optimising throughput, latency and cost across GPU and specialised accelerators. The role sits at the intersection of ML, systems engineering and MLOps, with direct impact on production workloads.
Key Requirements
- 4+ years of ML / systems engineering experience
- Deep experience with model quantisation, distillation or pruning
- Hands-on with TensorRT, ONNX Runtime, vLLM or similar inference runtimes
- Strong C++ or Python systems programming skills
- Experience deploying inference at scale in cloud or on-prem
Why Dubai?
Remote-first roles in global AI companies are a perfect fit for Dubai-based engineers who want top-tier compensation, tax advantages and the ability to work at the cutting edge of deep learning infrastructure.
Apply now: View full job listing on LinkedIn →