AI Training & Inference Acceleration Architect

Beijing Foreign Enterprise Management Consultants Co.,Ltd.; Singapore; Sur place; SGD 180 000 - 260 000; Plein temps

Résumé du poste

Huawei invites applications for an AI Training/Inference Acceleration Algorithm Engineer in Singapore. You will lead R&D of acceleration algorithms for Agentic AI and Multimodal domains, optimized for next-generation AI compute architectures to maximize efficiency.

You should have a strong background in LLM architectures and MoE models, with proven experience in large-scale training, fine-tuning, or inference deployment, plus hands-on AI acceleration tech and Python proficiency.

Qualifications

• Master's or PhD degree in Computer Science, AI, Electronic Engineering, or related field.
• Solid foundation in LLM architectures and MoE models with experience in large-scale training, fine-tuning, or inference.
• Hands-on experience in AI acceleration technologies and optimization techniques.

Responsabilités

• Lead R&D of AI training and inference acceleration algorithms for next-gen compute architectures.
• Implement acceleration algorithms within proprietary AI frameworks and libraries with iterative optimization.
• Identify trends and pre-plan algorithms to maintain competitive AI computing platforms.

Connaissances

Python programming

Distributed computing

Model optimization

AI acceleration concepts

High-performance kernels

Formation

Master's or PhD in Computer Science / AI / Electronic Engineering

Outils

Zero-redundancy optimizer techniques

Distributed parallel strategies (TP/PP/SP/VP/DP)

Memory optimization

KV-cache compression

Model weight/activation quantization

Description du poste

Huawei invites applications for an AI Training/Inference Acceleration Algorithm Engineer in Singapore. You will lead R&D of acceleration algorithms for Agentic AI and Multimodal domains, optimized for next-generation AI compute architectures to maximize efficiency.

You should have a strong background in LLM architectures and MoE models, with proven experience in large-scale training, fine-tuning, or inference deployment, plus hands-on AI acceleration tech and Python proficiency.