Machine Learning Engineer

Description of Role

As a Machine Learning Engineer based in Dubai, you will play a pivotal role in designing, optimizing, and scaling AI inference pipelines to meet enterprise demands for ultra-low latency and high throughput. In this capacity, you will collaborate closely with data scientists, software engineers, and IT operations to ensure robust, reliable, and cost-efficient AI delivery. Your work will directly impact mission-critical applications in domains such as finance, healthcare, and logistics, where real-time inference performance can drive significant business value.

Key Responsibilities:
* Architect and implement end-to-end AI inference systems using TensorRT, Triton Inference Server, vLLM, and FasterTransformer to achieve sub-10ms response times at scale.
* Develop model optimization workflows using ONNX conversion, quantization techniques (FP16, INT8, FP8), and GGUF format to reduce memory footprint and accelerate throughput.
* Maintain and extend distributed GPU workloads across multi-node clusters employing NCCL, MPI, InfiniBand, and RDMA for seamless scaling of training and inference jobs.
* Build and manage containerized AI infrastructure leveraging Kubernetes, OpenShift, Kubeflow, Ray, and KServe to automate deployment, scheduling, and monitoring of GPU resources.
* Implement observability and profiling pipelines with nvidia-smi, Nsight, nvprof, and TensorRT Profiler to proactively detect performance bottlenecks and ensure SLAs.
* Enforce enterprise-grade security, governance, and MLOps best practices, including version control, continuous integration, and automated testing for AI models in production.

What Makes This Opportunity Unique

Joining our team means working on cutting-edge AI infrastructure in a thriving, on-site environment in Dubai’s tech hub. You will benefit from:
* Hands-on experience with the latest deep learning inference frameworks and GPU acceleration techniques.
* A supportive culture with regular hackathons, technical brown-bag sessions, and knowledge-sharing forums.
* Assistance with relocation, visa sponsorship, and settling-in services to ensure a smooth transition to Dubai.
* Comprehensive medical insurance and wellness programs tailored for on-site employees.
* Interaction with global teams and exposure to large-scale, geographically distributed systems handling millions of transactions daily.

About Enfint

Enfint is a fast-growing AI infrastructure company specializing in enterprise-grade MLOps solutions. Our mission is to democratize high-performance model serving by delivering turnkey platforms that reduce time-to-market and operational complexities. Headquartered in Dubai, we pride ourselves on innovation, collaboration, and maintaining the highest standards of reliability. Our clients range from Fortune 500 financial institutions to leading healthcare providers, and we continually push the boundaries of what AI can achieve in real-time environments.