Remote AI Inference Engineer: Kernel & Edge Optimization

Lever, Inc.; Österreich; Remote; EUR 90.000 - 130.000; Vollzeit

Benefits dieser Stelle

Remote-first team

International collaboration

Cutting-edge AI research

Performance-critical infrastructure

Multimodal AI projects

Zusammenfassung

Lever, Inc. is seeking an AI Research Engineer (Kernel & Inference Optimization) based in Austria.

You will work at the intersection of AI research, systems engineering, and high-performance model inference, focusing on model-serving architectures across hardware environments including edge devices. The role blends hands-on research with low-level engineering to translate findings into measurable performance improvements.

Qualifikationen

• PhD in NLP, ML, or related field with strong AI research track record.
• Expertise in Metal Shading Language (MSL) with ability to write custom compute shaders from scratch.
• Experience with low-level kernel optimization and inference optimization on mobile or resource-constrained devices.
• Proven ability to deliver measurable improvements in inference latency, throughput, and memory footprint.
• Knowledge of distributed inference techniques: tensor, pipeline, and expert parallelism.
• Strong English communication and collaboration with distributed teams.

Aufgaben

• Design and deploy model-serving architectures optimized for high throughput and low latency.
• Develop inference pipelines for mobile and edge platforms.
• Set performance targets for latency, throughput, memory, and reliability.
• Build benchmarks and track latency, throughput, memory, and error rates.
• Create datasets and simulation scenarios for evaluating model performance under constraints.
• Identify bottlenecks and implement system-level optimizations.
• Develop GPU kernels and compute shaders for mobile hardware (MSL).
• Apply pruning, quantization, Flash Attention, KV caching, and speculative decoding.
• Design distributed inference using tensor, pipeline, and expert parallelism.

Kenntnisse

Metal Shading Language

Kernel optimization

Inference optimization

GPU kernels

Edge/mobile deployment

Distributed inference

Benchmarking

Communication in English

Ausbildung

PhD in NLP / ML

BSc in Computer Science

Tools

MSL tooling

Jobbeschreibung

Lever, Inc. is seeking an AI Research Engineer (Kernel & Inference Optimization) based in Austria.

You will work at the intersection of AI research, systems engineering, and high-performance model inference, focusing on model-serving architectures across hardware environments including edge devices. The role blends hands-on research with low-level engineering to translate findings into measurable performance improvements.