Edge Models Optimization Research Engineer

Huawei Italia; Toscana; Sur place; EUR 50 000 - 60 000; Plein temps

Résumé du poste

Huawei Italia cerca un ricercatore per l’Istituto di Pisa, nell’area software automobilistico ed embedded. Il candidato lavorerà sullo sviluppo di modelli intelligenti, tecniche post-training, MoE e ottimizzazione su piattaforme con vincoli di risorse, collaborando con team di system software, compiler e hardware.

Si richiede esperienza con PyTorch, conoscenza di modelli di grandi dimensioni e pubblicazioni/open-source; è apprezzata la capacità di pubblicare ricerche e guidare innovazioni.

Qualifications

• Master o PhD in Informatica, Intelligenza Artificiale, ML, Ingegneria Informatica o livello equivalente.
• Solida comprensione di transformer, modelli LLM e tecniche di deep learning moderne.
• Esperienza con PyTorch e framework di training distribuito; preferita ricerca su ottimizzazione di modelli, edge AI o foundation models.
• Pubblicazioni in conferenze di alto livello o contributi open-source considerati un punto di forza.

Responsabilités

• Indagare approcci post-training per modelli di grandi dimensioni e modelli multimodali.
• Esplorare architetture MoE ed inferenza sparsa entro vincoli di latenza/memoria/power.
• Sviluppare tecniche di compressione del modello (quantizzazione, pruning, low-rank adaptation) e ottimizzare l’inference su CPU/GPU/NPUs/SoC automotive.
• Benchmarking di modelli open-source e collaborare con piattaforme software per migliorare l’efficienza di deployment.

Connaissances

Transformer architectures

Large language models

PyTorch

Distributed training frameworks

Formation

Master or PhD in CS/AI/ML/CE

Outils

PyTorch

Distributed training frameworks

Description du poste

Questa posizione è in Huawei Italia

Il processo di selezione sarà interamente gestito Huawei Italia.

--

Position Summary: Huawei’s Pisa Research Institute is a core innovation hub in the field of automotive software and embedded systems. We are looking for a highly motivated researcher to join our AI platform team and contribute to the development of next-generation models for intelligent vehicles and edge computing systems. The successful candidate will focus on post-training techniques, efficient Mixture-of-Experts (MoE) architectures, and deployment optimization on resource-constrained platforms. Working closely with system software, compiler, and hardware teams, the candidate will help bridge cutting-edge AI research and real-world automotive applications. Key Responsibilities:

• Investigate advanced post-training approaches for large language models and multimodal foundation models, including supervised fine-tuning, preference alignment, reinforcement learning-based optimization, and knowledge distillation.
• Explore efficient MoE architectures and sparse inference mechanisms that enable high-quality intelligence under strict latency, memory, and power constraints.
• Develop and evaluate model compression techniques such as quantization, pruning, and low-rank adaptation, while also optimizing inference performance across heterogeneous computing platforms including CPUs, GPUs, NPUs, and automotive SoCs.
• The role further involves benchmarking state-of-the-art open-source models, collaborating with software platform teams to improve deployment efficiency, and contributing to research publications, patents, and technical innovation initiatives.

Basic Qualifications:

• Candidates should hold a master or PhD in Computer Science, Artificial Intelligence, Machine Learning, Computer Engineering, or a closely related field.
• A strong understanding of transformer architectures, large language models, and modern deep learning techniques is required.
• Experience with PyTorch and distributed training frameworks is expected, while previous research experience in model optimization, efficient AI, edge AI, or foundation models will be highly valued.
• Publications in top-tier conferences or demonstrated open-source contributions are considered a strong advantage.

What we offer: We offer an exciting career opportunity to contribute to shaping the future of automotive computing. You will join a multidisciplinary research team working on some of the most challenging topics in AI, software systems, and intelligent vehicles, driving innovation in next-generation mobility technologies. The position provides access to real-world datasets, large-scale computing resources, international collaboration opportunities, and a clear pathway to transform scientific research into impactful technologies deployed at scale. We offer a gross annual salary typically ranging from €50,000 to €60,000 determined according to objective criteria such as professional experience, competencies, and seniority. Employees may also be considered for a discretionary annual bonus ranging from 0 to 2 monthly salaries, subject to company evaluation. The applicable collective bargaining agreement is the CCNL Telecommunications, within level 6°.

--