Member of Technical Staff - ML Inference Engineer, Pytorch jobs in United States
cer-icon
Apply on Employer Site
company-logo

Liquid AI · 5 months ago

Member of Technical Staff - ML Inference Engineer, Pytorch

Liquid AI is a foundation model company spun out of MIT, focused on building efficient AI systems at every scale. The role of Member of Technical Staff - ML Inference Engineer involves optimizing and productionizing GPU model inference pipelines, facilitating the development of next-generation Liquid Foundation Models, and profiling the stack for various serving requirements.

Artificial Intelligence (AI)Foundational AIGenerative AIInformation TechnologyMachine Learning
check
H1B Sponsor Likelynote

Responsibilities

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

Qualification

PyTorchModel-serving frameworksLarge-scale production stacksPythonQuantization strategiesMulti-GPU environmentsDynamic load balancingKV-cache managementRagged batching

Required

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

Preferred

PyTorch
Python
Model-serving frameworks (e.g. TensorRT, vLLM, SGLang)

Company

Liquid AI

twittertwittertwitter
company-logo
Build efficient general-purpose AI at every scale.

H1B Sponsorship

Liquid AI has a track record of offering H1B sponsorships. Please note that this does not guarantee sponsorship for this specific role. Below presents additional info for your reference. (Data Powered by US Department of Labor)
Distribution of Different Job Fields Receiving Sponsorship
Represents job field similar to this job
Trends of Total Sponsorships
2025 (2)

Funding

Current Stage
Growth Stage
Total Funding
$293.1M
Key Investors
AMD VenturesOSS Capital L.P.
2024-12-13Series A· $250M
2023-12-01Seed· $37.5M
2023-05-05Seed· $5.6M

Leadership Team

leader-logo
Ramin Hasani
Co-founder and CEO
linkedin
leader-logo
Mathias Lechner
Co-founder and CTO
Company data provided by crunchbase