Senior GPU Systems Engineer: Large-Scale Inference & RL

Reflection; Greater London; On-site; GBP 70,000 - 100,000; Full time

Benefits offered by this job

Top-tier compensation

Comprehensive medical, dental, and vision insurance

Fully paid parental leave

Paid time off and relocation support

Daily lunch and dinner provided

Job summary

Reflection is seeking an experienced professional to design and operate large-scale GPU infrastructure for model inference and reinforcement learning. The role involves developing systems for high-performance inference platforms, optimizing GPU utilization, and diagnosing performance bottlenecks. Ideal candidates will have hands-on experience with GPU systems, knowledge of modern inference frameworks, and skills in debugging complex performance issues across distributed systems. The company offers competitive compensation and comprehensive benefits.

Qualifications

• Experience deploying and operating large-scale GPU systems for inference or model serving.
• Several years of hands-on experience building and running production infrastructure.
• Strong understanding of GPU performance characteristics and optimization techniques.
• Experience working with modern inference frameworks such as SGLang, Megatron, or similar.
• Familiarity with distributed reinforcement learning infrastructure.
• Experience optimizing throughput for large-scale model execution workloads.
• Experience working with GPU kernels or low-level performance optimization.
• Familiarity with infrastructure used for synthetic data pipelines.
• Experience debugging performance issues across GPU and networking.

Responsibilities

• Design, build, and operate large-scale GPU infrastructure for high-throughput model inference.
• Develop systems for synthetic data generation and reinforcement learning pipelines.
• Build high-performance inference platforms across thousands of GPUs.
• Optimize throughput and latency for large language model inference.
• Support distributed RL workloads and large-scale model evaluation infrastructure.
• Improve performance through kernel-level optimization and model parallelism.
• Diagnose and resolve performance bottlenecks in distributed compute systems.

Skills

Operating large-scale GPU systems

Building production infrastructure

GPU performance optimization

Inference frameworks (SGLang, Megatron)

Distributed reinforcement learning

Throughput optimization

GPU kernels debugging

Synthetic data pipelines

Performance issue debugging

Job description

Reflection is seeking an experienced professional to design and operate large-scale GPU infrastructure for model inference and reinforcement learning. The role involves developing systems for high-performance inference platforms, optimizing GPU utilization, and diagnosing performance bottlenecks. Ideal candidates will have hands-on experience with GPU systems, knowledge of modern inference frameworks, and skills in debugging complex performance issues across distributed systems. The company offers competitive compensation and comprehensive benefits.