ML Inference Engineer, PyTorch

About the Role

Join our innovative team as an ML Inference Engineer specializing in PyTorch, where you'll be instrumental in bringing cutting-edge machine learning models from research to high-performance production environments. This is a full-time, remote position open to candidates in the United States, Austria, Canada, France, Germany, Netherlands, Switzerland, and the UK.

Responsibilities

• Optimize PyTorch models for efficient and scalable inference across various hardware platforms.
• Design, develop, and maintain robust ML inference pipelines for production deployment.
• Collaborate closely with ML researchers to bridge the gap between model development and deployment.
• Implement and improve model serving infrastructure, ensuring high availability and low latency.
• Monitor model performance in production and troubleshoot inference-related issues.

Requirements

• Strong experience with PyTorch and its ecosystem for model development and deployment.
• Proven expertise in ML model optimization techniques (e.g., quantization, pruning, TorchScript, ONNX).
• Proficiency in Python and experience with C++ for performance-critical components.
• Solid understanding of machine learning fundamentals and deep learning architectures.
• Experience deploying ML models into production environments, including cloud or edge devices.

Nice-to-Haves

• Experience with distributed systems and large-scale ML deployments.
• Familiarity with various hardware accelerators (GPUs, TPUs, custom ASICs).
• Knowledge of cloud platforms (AWS, Azure, GCP) and containerization technologies (Docker, Kubernetes).
• Contributions to open-source ML projects, especially PyTorch.