Search
Go
AI Research Engineer, Model Compression & Quantization
Summary by AIEngineer.careers
AI Research Engineer, Model Compression & Quantization is a AI Research Engineer role (full-time). with Tether.io. in AMSTERDAM, NL. Imported listing (source: baan24.nl). Apply on the employer's site (baan24.nl).
Imported listing (source: baan24.nl) · Apply on baan24.nl
AMSTERDAM · NL
—
Full-time
MID
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from baan24.nl
Tether.io is seeking an AI Research Engineer focused on model compression, quantization, kernels, and inference optimizations. The role involves advancing efficient AI models and deployment techniques. This is an on-site position based in Amsterdam, Netherlands.
Responsibilities
- Research and develop model compression techniques
- Implement quantization methods for neural networks
- Optimize kernels and inference pipelines
- Collaborate with cross-functional teams to deploy efficient models
Requirements
- Experience in model compression and quantization
- Strong background in deep learning and optimization
- Proficiency in Python and ML frameworks (e.g., PyTorch, TensorFlow)
- Knowledge of GPU programming and kernel optimization
Nice to Have
- Experience with large-scale model deployment
- Publications in relevant AI conferences
Tech Stack
Inference Optimization
T
Tether.io
San Salvador Centro · SV · 322+ employees
Tether is a technology and financial-services company best known for issuing USD₮ (USDT), a blockchain-based stablecoin designed to track the U.S. dollar. Its broader activities include digital-asset and tokenization infrastructure, Bitcoin mining, peer-to-peer communications, education, AI, and neurotechnology initiatives.
