Staff Engineer - Large-Scale GPU Inference & RL Infra

Visa Hunt; San Francisco, Northern (CA, KY); Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Top-tier compensation

Stock options

Health & wellness benefits

Meals provided in office

22 weeks parental leave

Unlimited vacation (US)

Visa sponsorship

Team events

Job summary

Reflection is a research lab focused on making intelligence open and accessible. We design, build, and operate GPU-heavy infrastructure for high-throughput model inference and mid-training workloads.

Join a team that powers synthetic data generation, RL pipelines, and distributed model evaluation across thousands of GPUs. Expect collaboration with research teams and a focus on performance tuning, kernel optimization, and scalable distributed systems.

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 with modern inference frameworks such as SGLang, Megatron, or similar high-performance LLM runtimes.
• Familiarity with distributed reinforcement learning infrastructure or rollout generation systems.
• Experience optimizing throughput for large-scale model execution workloads.
• Experience working with GPU kernels or low-level performance optimization.

Responsibilities

• Design, build, and operate large-scale GPU infrastructure for high-throughput model inference and mid-training workloads.
• Develop systems that power synthetic data generation and reinforcement learning pipelines at scale.
• Build high-performance inference platforms capable of serving and evaluating models across thousands of GPUs.
• Diagnose and resolve performance bottlenecks across inference runtimes, GPU kernels, networking, and distributed compute systems.
• Work closely with research teams to support distributed RL workloads and large-scale model evaluation infrastructure.

Skills

GPU infrastructure

production infrastructure

GPU performance optimization

distributed RL infrastructure

inference frameworks

kernel-level optimization

distributed compute systems

throughput optimization

networking

Tools

Megatron

SGLang

Job description

Reflection is a research lab focused on making intelligence open and accessible. We design, build, and operate GPU-heavy infrastructure for high-throughput model inference and mid-training workloads.

Join a team that powers synthetic data generation, RL pipelines, and distributed model evaluation across thousands of GPUs. Expect collaboration with research teams and a focus on performance tuning, kernel optimization, and scalable distributed systems.