Job Description :

- Focus: scale-out all-flash file and object store; opportunities in KV cache, in-memory acceleration, and AI inference workloads

- Deep exposure to AI inference pipelines, modern backup, Splunk/Elastic, Kafka, and Spark

- Ideal for candidates with storage-domain expertise: KV stores, cache hierarchies, high-throughput data paths

Key areas :

- KV cache design, eviction policies, latency optimization in distributed storage

- Inference data paths: model serving, feature caching, AI/ML data flows

- Infrastructure subsystems: high availability, cluster orchestration, Linux kernel considerations, device/driver interactions

What youll do :

- End-to-end innovation from concept to shipped product; focus on KV caching and inference-ready storage

- Solve complex problems (cache coherency, concurrency) and interact with product/validation teams

- Collaborate with peers; mentor others; drive customer success

- Learn continuously about storage, AI data flows, and infrastructure

Minimum qualifications :

- Linux development experience; strong C/C++, Python, Java, or Go; solid OO fundamentals

- Strong data structures, algorithms, threads, synchronization

- Excellent communication

- Preferred: storage-domain experience (KV cache, in-memory data structures, accelerator integrations)

- Preferred: experience guiding architecture decisions; high-availability deployments

- BS in CS/IT/EE or related; advanced degrees a bonus