Senior Staff Inference Performance Engineer
d-Matrix · Santa Clara · Remote
Infrastructureremotestaff$175k–$265k
At a glance
Highlights
- Own end-to-end performance of inference workloads on internal and customer clouds.
- Profile first to isolate bottlenecks from scheduling to accelerator execution.
- Build lightweight telemetry and benchmarks that reach into prototype stacks.
What they offer
- Equity
- Bonus
Ideal candidate
Systems-minded performance detective who loves profiling-first debugging in messy, cross-layer systems. You own outcomes, collaborate directly, and stay energized by hard inference performance problems.
Requirements
- 8+ years of hands-on performance or systems engineering including cross-layer regressions
- Proven ability to find overhead via profiling in unfamiliar, sparsely documented systems
- Deep systems fundamentals including Linux internals, NUMA, CPU pinning, PCIe, memory, cache and networking
- Experience running performance-sensitive workloads on Kubernetes and closing orchestration overhead
- Working knowledge of LLM inference serving including batching, KV-cache
- Fluency with AI and agentic tools for investigation with discipline to verify against real data
- remote policy
- Remote available in the US
Lab profile
About d-Matrix
Pioneers memory-centric compute-in-memory chips and software for faster, energy-efficient AI inference.
What they build
- Digital in-memory compute inference chips
- Rack-scale AI inference systems
- AI inference software stack
Known for
- Compute-in-memory architecture
- Energy-efficient inference design
- Full-stack chips-to-systems expertise
Key facts
- Founded in 2019
- Headquartered in Santa Clara, California
- Backed by Temasek, Playground Global, and M12
Posted · Last seen