Edge AI Inference Architect: Kernel & Performance

Lever, Inc.; Spain (TX); Remote; USD 136,000 - 204,000; Full time

Job summary

Lever, Inc. is seeking an AI Research Engineer (Kernel & Inference Optimization) in Spain to push the boundaries of efficient AI systems.

You will work at the intersection of AI research, systems engineering, and high-performance model inference, delivering practical improvements across diverse hardware environments. You will develop and optimize model-serving architectures, write custom GPU kernels for mobile hardware (MSL), and apply pruning, quantization, and Flash Attention to reduce latency

Qualifications

• PhD in NLP, ML or related field with strong AI research track record.
• Experience in low-level kernel optimization for mobile or edge devices.
• Proven ability to translate research into optimized inference for production.

Responsibilities

• Design and deploy advanced model-serving architectures optimized for high throughput, low latency, and memory efficiency.
• Develop inference pipelines across mobile and edge platforms.
• Benchmark and document performance improvements against benchmarks.
• Create datasets and scenarios for evaluating model performance under constraints.
• Identify bottlenecks and implement system-level optimizations.

Skills

Model serving

Latency optimization

GPU kernels

Metal Shading Language

Empirical benchmarking

Distributed inference

Research-to-production

Education

PhD in NLP/ML

CS degree

Tools

MSL

Job description

Lever, Inc. is seeking an AI Research Engineer (Kernel & Inference Optimization) in Spain to push the boundaries of efficient AI systems.

You will work at the intersection of AI research, systems engineering, and high-performance model inference, delivering practical improvements across diverse hardware environments. You will develop and optimize model-serving architectures, write custom GPU kernels for mobile hardware (MSL), and apply pruning, quantization, and Flash Attention to reduce latency