Staff Machine Learning Engineer, ML Performance & Optimization
Is deze vacature iets voor u?
Mijn cv maken Maak uw cv en ontdek uw matchpercentage met deze functie — en met alle andere.
De functie
Take ownership as a Staff ML Engineer focused on ML performance and optimization across multi-platform deployments.
You will optimize neural architectures and systems for high performance on GPU/TPU hardware, including onboard and simulation platforms.
Develop post-training techniques like quantization and kernel-level optimizations to reduce latency and memory footprint for real-time constraints.
Experiment with new architectures (sparse models) and decoding strategies (speculative decoding) to boost inference speed.
Enhance training efficiency for large models and fine-tuning in data-heavy pipelines, while collaborating with ML infra, hardware, and research teams.
This hybrid role emphasizes hands-on optimization and cross-team collaboration to scale production-grade models.
You will optimize neural architectures and systems for high performance on GPU/TPU hardware, including onboard and simulation platforms.
Develop post-training techniques like quantization and kernel-level optimizations to reduce latency and memory footprint for real-time constraints.
Experiment with new architectures (sparse models) and decoding strategies (speculative decoding) to boost inference speed.
Enhance training efficiency for large models and fine-tuning in data-heavy pipelines, while collaborating with ML infra, hardware, and research teams.
This hybrid role emphasizes hands-on optimization and cross-team collaboration to scale production-grade models.
Bekijk de volledige vacature
Taken, profiel, vaardigheden en voordelen — maak gratis een account aan.
Al een account? Inloggen
Vergelijkbare vacatures
Andere functies die kunnen passen.