Senior Solutions Architect - KV Cache and AI Storage
Tasks
- Analyze performance profiles and identify bottlenecks
- Build end to end KV cache solutions
- Build reference architectures and best practice guides
- Deliver tech talks to support field teams and customers
- Drive PoCs and benchmarks to validate improvements
- Lead technical exploration with customer architects
- Translate customer difficulties into feature requests and roadmap input
Perks/Benefits
- N/A
Skills/Tech-stack
Bluefield | CMX | Caching | Cassandra | Ceph | Compression | DOCA | Distributed Storage | Dynamo KVBM | Eviction strategy | GPUDirect Storage | Inference Server | KV cache | Large Language Model | Large language model inference | Model Inference | NEMO | NVME SSD | Object storage | Offloading | Quantization | Redis | RocksDB | SGLang | Spectrum-X | TensorRT | TensorRT-LLM | Tiered memory | Transformer | Triton Inference | Triton Inference Server | VLLM
Education
Related jobs
-
Solutions Architect - Top AI Labs CNY 435K-500KArtificial Intelligence | C++ | Computer Systems | Data Structures | Distributed ComputingSenior-level Full TimeChina, Beijing1d ago
-
Agentic Inference | CUDA | Distributed Training | Docker | GPU ComputingSenior-level Full TimeChina, Beijing4d ago
-
Senior Deep Learning Solution Architect CNY 367K-490KC++ | Caching | Computer Architecture | Data Structures | Data transferSenior-level Full TimeChina, Beijing4d ago
-
Entry-level Full Time广州20d ago
-
Deep Learning Performance Architect CNY 417K-540KAnalysis | Deep learning | Hardware Architecture | JAX | OptimizationCompetitive salary | Generous benefitsSenior-level Full TimeChina, Shanghai1mo ago
-
NIM Solutions Architect CNY 439K-540KAI Computing | AI workflow | AI workflow design | C++ | CI/CDCareer growth opportunities | Flexible working hours | Health insurance | Professional development programsSenior-level Full TimeChina, Beijing1mo ago