Edge AI Research Engineer: Optimized Inference and Kernels

Tether Operations Limited; United States; Remote; USD 180,000 - 280,000; Full time

Job summary

Tether Operations Limited in the United States is seeking a senior ML/NLP engineer to design and deploy advanced model serving architectures for high-throughput, low-latency inference on edge and mobile devices. You will build tests, prepare datasets, analyze bottlenecks, and integrate optimized serving frameworks into production pipelines to meet demanding performance requirements.

We value empirical research, distributed inference experience, and a track record of delivering end-to-end

Qualifications

• Degree in Computer Science or related field; PhD in NLP or Machine Learning preferred.
• Deep understanding of model serving architectures and inference optimization.
• Experience with edge/mobile inference and latency-focused design.

Responsibilities

• Design and deploy state-of-the-art model serving architectures for high throughput and low latency.
• Build and monitor controlled inference tests in simulated and live production environments.
• Identify and prepare high-quality test datasets and simulation scenarios for low-resource devices.
• Analyze computational efficiency and diagnose bottlenecks in the serving pipeline.
• Integrate optimized serving and inference frameworks into production pipelines for edge and on-device applications.

Skills

Low-level optimizations

Inference optimization

Model serving architectures

Latency optimization

Experimentation & empirical research

Data-driven testing

Education

Degree in Computer Science or related field

PhD in NLP or Machine Learning preferred

Tools

Metal Shading Language (MSL)

GPU kernels for mobile devices

Distributed Inference Systems (Tensor, Pipeline, Expert Parallelism)

Pruning

Quantization

Flash attention

KV Cache

Speculative Decoding

Job description

Tether Operations Limited in the United States is seeking a senior ML/NLP engineer to design and deploy advanced model serving architectures for high-throughput, low-latency inference on edge and mobile devices. You will build tests, prepare datasets, analyze bottlenecks, and integrate optimized serving frameworks into production pipelines to meet demanding performance requirements.

We value empirical research, distributed inference experience, and a track record of delivering end-to-end