Remote AI Model Compression & Quantization Engineer

Framework Ventures; United States; Remote; USD 180,000 - 260,000; Full time

Job summary

Tether's AI model team seeks an engineer to drive model serving and inference architectures for advanced AI systems. You will optimize deployment across resource-constrained devices and edge platforms to deliver high throughput and low latency in real-world scenarios.

Collaborating with cross-functional teams, you will design robust inference pipelines, establish performance metrics, and push innovations in diffusion models, vision transformers, pruning, and quantization.

Qualifications

• A degree in Computer Science or related field; PhD in NLP/ML preferred.
• Knowledge of Metal Shading Language (MSL) and custom compute shaders.
• Experience in low-level kernel and inference optimization on mobile and edge devices.
• Understanding of modern model serving architectures and low-latency techniques.
• Proven ability to design end-to-end inference pipelines and evaluation frameworks.
• Experience with diffusion models and vision transformers.
• Familiarity with pruning, quantization, flash attention and KV cache.

Responsibilities

• Design and deploy state-of-the-art model serving architectures with high throughput and low latency across diverse environments.
• Build, run, and monitor controlled inference tests in simulated and live environments.
• Prepare high-quality test datasets and scenarios for real-world deployment challenges.
• Analyze bottlenecks and optimize serving pipelines for scalability on resource-constrained systems.
• Collaborate with cross-functional teams to integrate optimized frameworks into edge-ready production pipelines.

Skills

Model Serving

Inference Optimization

Edge Deployment

GPU Kernels

NLP & ML

Distributed Inference

Tensor Parallelism

Diffusion Models

Vision Transformers

Eagle Speculative Decoding

Education

PhD in NLP/ML

Degree in Computer Science or related field

Tools

Metal Shading Language (MSL)

Job description

Tether's AI model team seeks an engineer to drive model serving and inference architectures for advanced AI systems. You will optimize deployment across resource-constrained devices and edge platforms to deliver high throughput and low latency in real-world scenarios.

Collaborating with cross-functional teams, you will design robust inference pipelines, establish performance metrics, and push innovations in diffusion models, vision transformers, pruning, and quantization.