AI Research Engineer (Model Compression & Quantization)
Core
Drive innovation in model compression and efficient deployment for advanced multimodal AI systems (LLMs, VLMs) to enable high-performance AI on resource-constrained edge devices.
Role type
Senior IC AI Research Engineer (Model Compression & Quantization)
Builds
Scalable, low-memory, low-latency AI systems for edge devices (smartphones)
Domain
Fintech / AI / Multimodal Machine Learning
Deliverable
production ML models
Required skills
Model quantization (QAT, PTQ), Knowledge distillation, Model pruning, Transformer architectures, PyTorch, Mixed-precision quantization
Preferred skills
C++ (for low-level kernels), PhD in NLP/ML, Publications in top-tier conferences (NeurIPS, ICML, etc.)
Technologies
PyTorch, LLMs, VLMs
Responsibilities
Apply low-bit quantization to reduce model size and latency; Leverage knowledge distillation for efficient multimodal reasoning; Implement pruning techniques to remove redundant parameters; Analyze trade-offs between efficiency and accuracy; Research and apply mixed-precision quantization and advanced compression strategies; Document methodologies and author technical papers for top-tier conferences.
Seniority
Senior, hands-on IC