Senior Modeling Architect, Performance Benchmarking
Neurophos · Austin, Texas · Sunnyvale, California
Infrastructureonsitesenior$210k–$250k
At a glance
Highlights
- Own performance and energy metrics for T100 optical inference accelerator.
- Set measurement methodology across models, software and hardware generations.
- Shape architecture decisions with measured performance and energy data.
What they offer
- 100% coverage of base health plan premiums plus HSA contributions
- Unlimited PTO
- 401(k) matching and stock option opportunities
- Voluntary dental, vision, life and supplemental insurance
Ideal candidate
A rigorous performance engineer who loves owning the numbers behind hardware decisions and making results reproducible. Thrives in startup ambiguity and partners closely with architects and leadership.
Requirements
- BS or MS in Computer Engineering, Electrical Engineering, Computer Science, or equivalent practical experience
- 5+ years of experience
- Knowledge of precision (FP16, BF16, FP8, INT8) and batching
- Working knowledge of LLM inference stacks such as Hugging Face, vLLM, SGLang, or TensorRT-LLM, including prefill versus decode, continuous batching, and MoE
- Proficiency in Python for harnesses, parsing, and plots, and comfort working in Linux
- Cloud GPU operations on AWS, GCP, or Azure, including containers, instance types, drivers, quotas, and cost
Lab profile
About Neurophos
Building silicon photonics chips for energy-efficient AI inference compute.
What they build
- Silicon photonics inference compute chips
Known for
- Silicon photonics
- Analog and SoC design
- Quantization and numerical optimization
- Performance modeling and benchmarking
Posted · Last seen