Magic
Member of Technical Staff, Inference & RL Systems
$275K–$550K
San Francisco · On-site · Staff · Full-time · Posted Feb 28, 2026
- Visa sponsorship
- Visa sponsorship is available, if possible.
About the job
Designs and operates distributed systems for production model inference and large-scale RL and post-training workflows.
What you'll do
- Design and scale inference serving systems, optimizing KV-cache management, batching, scheduling, latency, and throughput.
- Build and maintain distributed RL and post-training infrastructure, including reliable rollout, evaluation, and reward pipelines.
- Automate fault detection and recovery and profile performance across GPU, networking, and storage layers.
What they ask for
- Strong software engineering and distributed systems fundamentals.
- Experience building or operating large-scale inference or training systems.
- Deep understanding of GPU execution constraints and memory trade-offs.
- Experience debugging performance issues in production ML systems and owning critical production infrastructure.
Pay
$275K - $550K USD base salary
Tools
GPU
AI focus
Supports model inference and large-scale RL and post-training workflows, including rollout, evaluation, and reward pipelines.
Model-written summary · the original posting is authoritative