Engineering

Business Development

Sales

Information Technology

Entrepreneurship

Production AI inference infrastructure with lower cost and latency

Co-Founder

Machine Learning Researcher

Inference.net trains and hosts specialized language models for companies seeking frontier-quality AI at lower cost. The Machine Learning Researcher will conduct research on experimental models, training systems, and modalities, with a focus on LLM post-training, model efficiency, rigorous experimentation, and bringing successful research into production.

Inference.net is a company that trains and hosts specialized language models for businesses seeking high-quality AI solutions. The Machine Learning Researcher will conduct research into experimental models and training systems, aiming to develop novel products and improve model performance for customers.

Applied Machine Learning Engineer

Inference.net is a company that trains and hosts specialized language models for businesses seeking high-quality AI solutions at lower costs. The Applied Machine Learning Engineer will build and improve core ML systems, lead projects from data intake to trained models, and ensure high model quality at scale.

Senior Software Engineer - Model Performance

Inference.net is a company that trains and hosts specialized language models for businesses needing high-quality AI solutions. They are seeking a Senior Software Engineer - Model Performance to enhance their inference stack's speed and efficiency, focusing on implementing optimization techniques and improving performance across their systems.

Inference.net trains and hosts specialized language models and provides an end-to-end platform for model distillation, training, evaluation, and large-scale hosting. The Senior Software Engineer will optimize the inference stack for latency, throughput, cost efficiency, and scalable model serving by improving CUDA kernels, inference frameworks, and production systems.

inference.net