Senior Research Engineer / Scientist - Storage for LLM
This position is no longer accepting applications(closed Aug 17, 2026).
Summary
Design and build GPU-aware caching layers and distributed KV cache systems to optimize LLM token streaming and memory efficiency.
- Build custom GPU aware caching layers
- Design distributed KV cache system
- Evaluate and extend open source KV stores
- Implement cache consistency and synchronization protocols
- Implement memory aware sharding and replication
- Integrate cache with token streaming pipelines
- Monitor system performance and iterate caching algorithms
- Optimize cache latency and eviction policies
Perks/Benefits:
- Conference attendance
- Open source contributions
- Research resources