Senior ML Performance Engineer — Ultra-Fast Inference + Equity

well-funded deeptech startup; California (MO); On-site; USD 200,000 - 250,000; Full time

Job summary

Join a well-funded deeptech startup in California as a Senior ML Performance Engineer. You will lead the optimization of ML inference pipelines and improve model performance for innovative clients.

This role requires strong skills in Python, TensorFlow, and PyTorch, as well as expertise in performance optimization techniques. The ideal candidate is eager to work on cutting-edge ML projects in an energetic environment with potential for significant impact.

Qualifications

• Strong proficiency in Python and ML frameworks such as TensorFlow and PyTorch.
• Deep understanding of ML algorithms and architectures.
• Expertise in performance optimization techniques including profiling and quantization.

Responsibilities

• Conduct in-depth performance profiling and analysis of ML models.
• Design and implement efficient ML inference pipelines.
• Collaborate with infrastructure teams to optimize configurations.

Skills

Python

TensorFlow

PyTorch

Performance optimization techniques

Kubernetes

AWS

GCP

Azure

Job description

Join a well-funded deeptech startup in California as a Senior ML Performance Engineer. You will lead the optimization of ML inference pipelines and improve model performance for innovative clients.

This role requires strong skills in Python, TensorFlow, and PyTorch, as well as expertise in performance optimization techniques. The ideal candidate is eager to work on cutting-edge ML projects in an energetic environment with potential for significant impact.