AI Research Engineer (Kernel & Inference Optimization)

United States Digital Space LLC; Deutschland; Remote; EUR 120.000 - 190.000; Vollzeit

Benefits dieser Stelle

Remote-first

International team

Cutting-edge AI research

Flexible work hours

Competitive compensation

Zusammenfassung

United States Digital Space LLC is seeking a research/engineering professional to advance model-serving architectures across mobile and edge hardware. You will develop and optimize inference pipelines, run rigorous benchmarks, and push performance through GPU kernels, quantization, and memory management.

Collaboration with distributed teams is central in a remote environment. The role emphasizes empirical research, reproducible evaluations, and scalable inference across diffusion models and

Qualifikationen

• PhD in NLP/ML or related with AI research track record.
• Proven experience writing GPU kernels for mobile or constrained devices.
• Expertise in model-serving architectures and latency optimization.
• Strong track record delivering measurable latency/throughput/memory gains.
• Experience with distributed inference on large-scale GPUs.

Aufgaben

• Design and deploy high-throughput, low-latency model-serving architectures.
• Develop inference pipelines for mobile and edge platforms.
• Benchmark latency, throughput, memory, and reliability in production.
• Identify bottlenecks and implement system-level optimizations.
• Create datasets and simulations to evaluate real-world performance.
• Collaborate with cross-functional teams to integrate optimized frameworks.

Kenntnisse

MSL GPU kernels

Low-level optimization

Distributed inference

Model serving

English communication

Ausbildung

PhD in NLP/ML

CS degree

Tools

MSL (Metal Shading Language)

Flash Attention

KV caching

Jobbeschreibung

You will work at the intersection of AI research, systems engineering, and high-performance model inference.Your focus will be on developing and optimizing model-serving architectures for advanced AI systems across a range of hardware environments.You will tackle challenges involving latency, throughput, memory efficiency, and scalability, including deployment on resource-constrained mobile and edge devices.The role combines hands-on research with low-level engineering, giving you the opportunity to develop novel inference strategies and GPU kernels.You will work with complex architectures spanning text, image, audio, diffusion models, and vision transformers.Your work will involve rigorous benchmarking, production testing, and iterative optimization to translate research into measurable performance improvements.You will collaborate with cross-functional teams in a highly technical, remote environment focused on pushing the boundaries of efficient AI systems.

Accountabilities

• Design and deploy advanced model-serving architectures optimized for high throughput, low latency, and efficient memory utilization.
• Develop inference pipelines capable of operating effectively across diverse environments, including resource-constrained mobile devices and edge platforms.
• Establish clear performance targets covering response latency, token generation speed, throughput, memory footprint, and reliability.
• Build and execute controlled inference benchmarks in simulated and production environments, tracking latency, throughput, memory consumption, and error rates.
• Create and maintain representative datasets and simulation scenarios for evaluating model performance under real-world and resource-constrained conditions.
• Identify computational and memory bottlenecks across inference pipelines and implement solutions involving batching, networking, memory management, and other system-level optimizations.
• Develop custom GPU kernels and compute shaders for mobile hardware, including solutions written in Metal Shading Language (MSL).
• Apply advanced inference optimization techniques such as pruning, quantization, Flash Attention, KV caching, and speculative decoding.
• Design and optimize distributed inference systems using approaches such as tensor parallelism, pipeline parallelism, and expert parallelism for large-scale GPU workloads.
• Work with cross-functional engineering and research teams to integrate optimized inference frameworks into production and edge-device applications.
• Define evaluation methodologies, document experimental results, compare performance against established benchmarks, and continuously refine optimization strategies.
• Monitor production performance and use empirical research to identify opportunities for further improvements in scalability, efficiency, and reliability.

Requirements

• Degree in Computer Science or a related technical field; a PhD in NLP, Machine Learning, or a related discipline is highly relevant, particularly with a strong AI research track record and publications at leading conferences.
• Proven expertise in Metal Shading Language (MSL), including the ability to write custom compute shaders from scratch.
• Demonstrated experience with low-level kernel optimization and inference optimization on mobile or other resource-constrained devices.
• Track record of delivering measurable improvements in inference latency, throughput, and memory footprint for domain-specific applications.
• Deep understanding of modern model-serving architectures, inference engines, and optimization techniques for high-performance AI deployment.
• Strong experience writing GPU kernels for mobile devices such as smartphones.
• Practical experience developing and deploying end-to-end inference pipelines, from model optimization through production integration on constrained hardware.
• Strong ability to apply empirical research and systematic experimentation to solve latency, computational, and memory challenges.
• Experience designing robust evaluation and benchmarking frameworks for inference systems.
• Knowledge of distributed inference techniques, including tensor parallelism, pipeline parallelism, and expert parallelism for large-scale GPU clusters.
• Deep understanding of the mathematical foundations and architecture of diffusion models and Vision Transformers.
• Familiarity with modern inference optimization techniques including pruning, quantization, Flash Attention, KV Cache optimization, and speculative decoding such as EAGLE.
• Strong analytical and problem-solving abilities, with an ability to investigate complex system bottlenecks and turn research findings into practical engineering solutions.
• Excellent English communication skills and the ability to collaborate effectively with distributed, cross-functional technical teams.

Benefits

• Opportunity to work on advanced AI systems spanning model serving, inference optimization, mobile computing, edge deployment, and large-scale distributed inference.
• Remote-first working environment with an international team.
• Exposure to cutting-edge AI research and practical systems engineering challenges.
• Opportunity to contribute to performance-critical infrastructure where improvements can have a measurable impact on real-world AI applications.
• Collaborative environment combining research-driven experimentation with hands-on engineering.
• Opportunity to work with advanced model architectures including diffusion models, Vision Transformers, and multimodal systems.
• Access to challenging technical problems involving GPU kernels, inference engines, memory optimization, and distributed computing.