Member of Technical Staff - ML Inference Engineer, PyTorch

Job not on LinkedIn

August 9

Apply Now

Receive Emails with Similar Jobs

Liquid AI

WebsiteLinkedInAll Job Openings

Artificial Intelligence • B2B • Enterprise

Liquid AI is a cutting-edge technology company that specializes in edge-native artificial intelligence solutions. Their innovative Liquid Foundation Models (LFMs) are designed to deliver efficient, customizable AI for various environments—from edge computing to cloud infrastructures. By maximizing compute efficiency and leveraging advanced neural network architectures, Liquid AI provides businesses with flexible and powerful AI solutions tailored to their specific needs.

51 - 200 employees

Founded 2023

🤖 Artificial Intelligence

🤝 B2B

🏢 Enterprise

📋 Description

• Optimize and productionize the end-to-end pipeline for GPU model inference around Liquid Foundation Models (LFMs). • Facilitate the development of next-generation Liquid Foundation Models from the lens of GPU inference. • Profile and robustify the stack for different batching and serving requirements. • Build and scale pipelines for test-time compute.

🎯 Requirements

• You have experience building large-scale production stacks for model serving. • You have a solid understanding of ragged batching, dynamic load balancing, KV-cache management, and other multi-tenant serving techniques. • You have experience with applying quantization strategies (e.g., FP8, INT4) while safeguarding model accuracy. • You have deployed models in both single-GPU and multi-GPU environments and can diagnose performance issues across the stack. • PyTorch • Python • Model-serving frameworks (e.g. TensorRT, vLLM, SGLang)

🏖️ Benefits

• Hands-on experience with state-of-the-art technology at a leading AI company. • Deeper expertise in machine learning systems and efficient large model inference. • Opportunity to scale pipelines that directly influence user latency and experience with Liquid's models. • A collaborative, fast-paced environment where your work directly shapes our products and the next generation of LFMs.