Sail Research
Member of Technical Staff - Distributed Systems
$200K–$300K
San Francisco · On-site · Staff · Full-time · Posted May 18, 2026
About the job
Design and build globally distributed control-plane systems that schedule, route, and monitor AI inference workloads for speed, reliability, and cost efficiency.
What you'll do
- Implement high-performance schedulers for admission control, queuing, priority, fairness, preemption, and bin packing.
- Build global routing and traffic management, including latency-aware dispatch, predictive autoscaling, failover, and cache-aware routing.
- Develop LLM-specific routing optimizations and observability across GPU RAM, CPU RAM, and NVMe flash.
What they ask for
- Strong distributed systems fundamentals, including concurrency, networking, databases, queues, and performance engineering.
Nice to have
- Experience with ML inference stacks (vLLM/SGLang), GPUs/accelerators, or high-RPS systems such as trading or messaging.
Pay
USD 200K – USD 300K base salary
Tools
vLLM, SGLang, GPU RAM, CPU RAM, NVMe flash
AI focus
Build infrastructure for AI inference and agent hosting, including LLM-specific routing and KV caching optimizations.
Model-written summary · the original posting is authoritative