AI Inference Engineer - Kernel & Edge Optimization

Jobgether SRL; United States; Remote; USD 82,000 - 177,000; Full time

Benefits offered by this job

Remote-first team

Exposure to cutting-edge AI research

Collaborative engineering environment

Job summary

Jobgether SRL is seeking an AI Research Engineer (Kernel & Inference Optimization) to advance model-serving architectures for diverse hardware and edge devices. You will blend hands-on research with low-level engineering to push latency, throughput, and memory efficiency while targeting mobile and edge platforms.

Collaborating with cross-functional, remote teams, you will benchmark, test, and translate research into scalable production solutions, including diffusion models, Vision Transformers,

Qualifications

• PhD in NLP/ML or related field with AI research track record.
• Proven expertise with MSL and custom compute shaders.
• Experience with low-level kernel and inference optimization on mobile/resource-constrained devices.
• Track record of improving inference latency, throughput, and memory footprint.
• Strong understanding of model-serving architectures and optimization techniques.
• Experience writing GPU kernels for mobile devices.
• Proven ability to develop end-to-end inference pipelines for production.
• Strong empirical research and systematic experimentation capabilities.
• Familiarity with distributed inference techniques for large-scale GPUs.

Responsibilities

• Design and deploy advanced model-serving architectures for high throughput and low latency.
• Develop inference pipelines across diverse environments including edge devices.
• Set clear performance targets for latency, throughput, memory, and reliability.
• Create controlled benchmarks to track latency, throughput, memory use, and errors.
• Develop datasets and simulations for evaluating performance.
• Identify bottlenecks and implement system-level optimizations.
• Build custom GPU kernels and compute shaders for mobile hardware (MSL).
• Apply pruning, quantization, Flash Attention, KV caching, and speculative decoding.
• Design distributed inference systems using tensor/pipeline/expert parallelism.
• Collaborate to integrate optimized inference into production and edge apps.
• Document experiments and refine optimization strategies based on results.
• Monitor production performance and identify scalability improvements.

Skills

Low-level kernel optimization

Inference optimization

Empirical research

English communication

System design

GPU performance tuning

Education

PhD in NLP/ML or related field

Master's degree in CS

Tools

Metal Shading Language (MSL)

GPU kernels

Inference frameworks

Quantization

Job description

Jobgether SRL is seeking an AI Research Engineer (Kernel & Inference Optimization) to advance model-serving architectures for diverse hardware and edge devices. You will blend hands-on research with low-level engineering to push latency, throughput, and memory efficiency while targeting mobile and edge platforms.

Collaborating with cross-functional, remote teams, you will benchmark, test, and translate research into scalable production solutions, including diffusion models, Vision Transformers,