AI Systems Engineer

Huawei’s Hilbert Research Center mission is to explore programming models, operating system and virtualization technologies on multicore heterogeneous architectures and NVM/SCM platforms, aiming to provide a high-performance, reliable abstraction layer for efficient resource utilization. DRC focuses its technical research in the key areas of Smart Mobile, Telecom, Autonomous Driving, Internet of Things, and Industry 4.0.

Join us as an AI Systems Engineer to bring intelligent agents to life on real-world devices. You’ll work on squeezing every ounce of performance out of modern mobile hardware, optimizing deep learning models for low-latency, battery-friendly inference. If “running AI inferences on edge” makes your eyes sparkle, this one’s for you.

Join us as a

AI Systems Engineer   (m/f/d)

• Deliver efficient, on-device AI inference by optimizing machine learning models for mobile and resource-constrained platforms—enabling fast, reliable, and privacy-preserving user experiences.

• Engineer performance-critical systems that balance power consumption, latency, and accuracy across various hardware targets such as ARM CPUs, mobile GPUs, and NPUs.

• Collaborate closely with AI and Systems engineers to translate cutting-edge model architectures into production-ready implementations.

• Build robust deployment pipelines using tools like TensorFlow Lite or custom runtimes to ensure scalable delivery and monitoring of edge AI workloads.

• Champion edge-first intelligence by designing solutions that reduce cloud dependency, improve responsiveness, and enhance user data privacy.

• BSc/Master or PhD in Computer Science or other related disciplines

• Machine learning engineering – Strong foundations in ML workflows, model evaluation, and integration of inference pipelines into production apps.

• Mobile AI deployment – Experience with deploying machine learning models on mobile platforms.

• Low-level performance tuning – Familiarity with ARM architecture, mobile GPUs/NPUs, and efficient use of hardware acceleration.

• Experimentation & benchmarking – Comfortable with profiling tools, A/B testing, and performance monitoring on-device to ensure optimal runtime behavior.

• Model optimization – Things like pruning, quantization, or distillation can really help on-device AI shine. If you’ve played with these or are excited to learn, that’s a plus.

• Fluent in written and spoken English

By applying to this position, you agree with our Recruitment Privacy Statement. You can read in full our privacy policy here.