AI Inference Engineer

Summary

Join Tether, a company committed to making advanced AI technologies more accessible, and build the next generation of AI models. We are building AI solutions for various applications, from large-scale models to smaller, efficient models for edge devices. Our dynamic, fully remote team is rapidly growing and innovating within the AI industry. This role focuses on deploying machine learning models to edge devices and collaborating with researchers to transition models from research to production. We are seeking individuals with strong programming skills and experience in AI/ML to help us exceed the capabilities of current AI leaders.

Requirements

• Have excellent programming skills in Python, C and C++
• Have experience with platforms such as TVM, MLC, and IREE (MLIR), which facilitate the deployment of models to specific GPU architectures
• Have experience in NLP, computer vision, TensorFlow, PyTorch, JAX and CUDA toolkit
• Have experience with different aspects of Large Language Models (LLMs), such as fine-tuning techniques to tailor models to specific tasks and prompt engineering
• Have extensive experience in training models using multi-GPU setups
• Demonstrate the ability to rapidly assimilate new technologies and techniques
• Have a degree in Computer Science, AI, Machine Learning, or a related field, complemented by a solid track record in AI R&D

Responsibilities

• Work on deploying machine learning models to edge devices using frameworks such as TVM, MLC, and IREE (MLIR)
• Collaborate closely with researchers to assist in coding, training and transitioning models from research to production environments
• Integrate AI features into existing products, enriching them with the latest advancements in machine learning