On-Device AI Quantization Engineer for LLMs & VLMs

XG TECH PTE.LTD.; Santo Niño 1st; On-site; PHP 1,674,000 - 2,344,000; Full time

Job summary

XG Tech PTE.LTD. in the Philippines is seeking a Large Model Quantization Algorithm Engineer to develop and optimize quantization and model compression for LLMs, VLMs, and video models.

You will improve accuracy, reduce memory use, and boost on-device inference across NPUs, GPUs, and CPUs, collaborating with compiler and hardware teams for production deployment. The role emphasizes PTQ/QAT methods, cross-hardware adaptation, and building automation tools for quantization workflows, with a focus

Qualifications

• Bachelor’s degree or above in a quantitative field.
• Familiarity with LLM/VLM algorithms and deployment optimization techniques, including model quantization, sparsity/pruning, and inference acceleration frameworks.
• Prior hands-on experience with PyTorch Quantization-Aware Training (QAT) development is advantageous.
• Strong proficiency in Python and C++.

Responsibilities

• Develop and optimize quantization algorithms for LLMs, VLMs, and video generation models, covering PTQ, QAT, and related model compression techniques.
• Design and evaluate quantization schemes to balance model accuracy, inference performance, and memory efficiency.
• Perform quantization calibration and error analysis, identifying sources of accuracy degradation and driving optimization solutions.
• Optimize edge and on-device inference, including Prefill/Decode acceleration, KV Cache management, operator fusion, weight compression, and memory optimization.
• Adapt and deploy models across heterogeneous hardware, including NPU and CPU platforms, working closely with compiler teams on model conversion, engine compilation, and performance tuning.
• Develop quantization and model optimization toolkits, including automated quantization workflows, accuracy evaluation, and visualization/debugging tools.
• Collaborate with model and architecture teams to develop quantization-friendly model architectures, training strategies, and inference optimization techniques.
• Track and evaluate emerging research in model quantization, compression, sparsity, and efficient inference, and drive relevant techniques into production.

Skills

Python

C++

PyTorch QAT

Quantization

Edge deployment

Education

Bachelor’s degree or above in Electronics Engineering, Computer Science, Automation, Operations Research, Statistics, Mathematics

Job description

XG Tech PTE.LTD. in the Philippines is seeking a Large Model Quantization Algorithm Engineer to develop and optimize quantization and model compression for LLMs, VLMs, and video models.

You will improve accuracy, reduce memory use, and boost on-device inference across NPUs, GPUs, and CPUs, collaborating with compiler and hardware teams for production deployment. The role emphasizes PTQ/QAT methods, cross-hardware adaptation, and building automation tools for quantization workflows, with a focus