Remote AI Kernel & Inference Engineer

Tether; Job; Híbrido; USD 180 000 - 260 000; Tempo integral

Resumo da oferta

Tether is seeking a senior AI/ML engineer to advance model serving and inference for real-world fintech applications. You will optimize deployment pipelines across devices, from mobile to edge, focusing on low latency, memory efficiency, and scalable performance.

Ideal candidates hold a PhD in NLP/ML and have proven experience with diffusion models, vision transformers, and GPU-accelerated inference. Remote work is available with international collaboration and growth opportunities.

Qualificações

• PhD in NLP or ML preferred and strong AI R&D background.
• Deep expertise in designing and optimizing model serving pipelines.

Responsabilidades

• Design and deploy state-of-the-art model serving architectures for high throughput and low latency across devices.
• Build and monitor inference tests in simulated and live environments with KPIs.
• Identify test datasets and simulations for real-world edge deployment challenges.
• Analyze bottlenecks in serving pipelines and optimize memory/compute usage.
• Collaborate with cross-functional teams to integrate serving frameworks into production pipelines.

Conhecimentos

Model Serving

Inference

Edge Devices

GPU Kernels

Metal Shading Language

Diffusion Models

Vision Transformers

Pruning

Quantization

Flash attention

KV Cache

Speculative Decoding

Formação académica

PhD in NLP

Ferramentas

Metal Shading Language (MSL)

Descrição da oferta de emprego

Tether is seeking a senior AI/ML engineer to advance model serving and inference for real-world fintech applications. You will optimize deployment pipelines across devices, from mobile to edge, focusing on low latency, memory efficiency, and scalable performance.

Ideal candidates hold a PhD in NLP/ML and have proven experience with diffusion models, vision transformers, and GPU-accelerated inference. Remote work is available with international collaboration and growth opportunities.