Senior Staff Inference Performance Engineer
1 hour agoLeadSalary: 175K - 265KSanta Clara, CA / Remote, USRemoteFull TimeEngineeringJobs by d-Matrix
d-MatrixVisit d-Matrix website
AI-infrastructure company producing memory-centric hardware, networking, and software for low-latency generative-AI inference in data centers.
Santa Clara, United States
Funding history
About d-Matrix
d-Matrix develops digital in-memory-compute technology and a full-stack inference platform comprising Corsair accelerators, JetStream networking accelerators, and Aviator software.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will diagnose performance across orchestration and inference systems, isolate root causes, and improve workload performance against bare metal. You will build telemetry and benchmarks, capture deployment requirements, create playbooks, and mentor engineers.
Requirements
- 8+ years of performance or systems engineering experience
- Performance profiling
- Linux internals
- NUMA
- CPU pinning
- cpusets
- PCIe
- Memory and cache behavior
- Networking
- Kubernetes
- LLM inference serving
- Batching
- KV-cache
- Prefill and decode
- Quantization
- Speculative decoding
- Python
- C/C++
- Technical writing
- AI and agentic tools
Responsibilities
- Diagnose performance across orchestration, networking, autoscaling, inference, drivers, runtimes, operating systems, and accelerators.
- Isolate problems to the responsible layer and team.
- Write reproducible cross-stack problem statements.
- Improve throughput, latency, and stability against bare-metal performance.
- Assess fleet-scale routing, placement, and resource contention.
- Capture node requirements in orchestration configuration.
- Build telemetry and benchmarks for prototype stacks.
- Create investigation playbooks and mentor engineers.
Benefits
- Equity
- Bonus
- Medical insurance
- Dental insurance
- Vision insurance
- 401(k)
- Performance-based incentive opportunities