Remote AI Kernel & Inference Engineer

Tuxcare Inc.; Neuquén; Remote; ARS 138,361,000 - 230,602,000; Full time

Job summary

Tether is seeking an AI Research Engineer focused on kernel and inference optimization for highly scalable model serving. You will optimize deployment strategies across resource-constrained devices and edge platforms, pushing the performance envelope in low-latency AI applications.

Join a globally distributed team, contribute to cutting-edge AI systems, and drive efficient, scalable inference in real-world fintech and data-sharing products.

Qualifications

• A degree in Computer Science or related field; PhD in NLP/ML preferred with publications in AI R&D.
• Knowledge of Metal Shading Language (MSL) and ability to write custom compute shaders from scratch.
• Proven experience in low-level kernel and inference optimization on mobile devices; measurable latency/throughput improvements.

Responsibilities

• Design and deploy state-of-the-art model serving architectures for high throughput and low latency on edge/mobile hardware.
• Build, run, and monitor controlled inference tests in simulated and real production environments; track latency, throughput and memory metrics.
• Identify and prepare high-quality test datasets and scenarios for real-world deployment on low-resource devices.
• Analyze bottlenecks in the serving pipeline and optimize memory usage and throughput across platforms.
• Collaborate with cross-functional teams to integrate optimized serving frameworks into edge-produced pipelines.

Skills

GPU kernel programming

Model serving

Inference optimization

Metal Shading Language

Low-level optimization

Education

Bachelor/Master/PhD in CS or related

PhD in NLP/ML (preferred)

Tools

MSL

Mobile device GPUs

Job description

Tether is seeking an AI Research Engineer focused on kernel and inference optimization for highly scalable model serving. You will optimize deployment strategies across resource-constrained devices and edge platforms, pushing the performance envelope in low-latency AI applications.

Join a globally distributed team, contribute to cutting-edge AI systems, and drive efficient, scalable inference in real-world fintech and data-sharing products.